Alexa Scientists Address Challenges of End-Pointing

Just as Alexa can wake up without the need to press a button, she also automatically detects when a user finishes her query and expects a response. This task is often called “end-of-utterance detection,” “end-of-query detection,” “end-of-turn detection,” or simply “end-pointing.”

The challenges of end-pointing are two-fold: On the one hand, we don’t want Alexa to be too eager to reply and potentially cut a user off during a speech pause or while the user is just taking a breath (we call this an “early end-point”). On the other hand, Alexa also should not wait too long before replying to the user query (or even mistakenly consider background speech as device-directed and continue listening) since this is perceived as high latency by the customer (we call such cases “late end-points”).

The ideal end-pointer knows to distinguish speech pauses or hesitation from final pauses, in order to trigger instantly after a query ends while remaining patient in cases of hesitation (note: in online or streaming speech recognition systems, the input speech signal is not observed all at once but received in small chunks and processed in real-time). Given sufficient example data, the design of an end-pointer algorithm can be considered a machine learning problem.

Next week, at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018, my colleagues and I will present a paper that proposes an end-of-utterance detection system that allows for resource-efficient adaptation for new domains and across languages. More specifically, we train a machine learning model to estimate, for an observed segment of audio, whether the segment is “complete” (i.e., containing a full user query) or whether more speech input is expected.

Roland_Maas_EP2_._CB498703590_.png
The proposed end-point detector based on three feature types: acoustic embeddings, ASR hypothesis embeddings, and decoder features

The model comprises three components: an acoustic classifier, a word-based classifier, and a final classification layer that combines the previous classifiers and additional meta-features from the automatic speech recognition (ASR) system to form a final decision.

Let’s look at each component individually. The acoustic classifier is a long-short-term-memory (LSTM) recurrent neural network that, on its input side, consumes a short snippet of audio (typically in the order of 25 milliseconds). On its output side, the classifier emits a probability (between 0 and 1) of how likely the segment of audio (absorbed so far) constitutes a complete user query. As a result, the acoustic classifier should learn different acoustic patterns that indicate whether a speech pause is final or not. Cues that indicate an end of turn in human-to-human conversations (that the network may implicitly learn) include speaking rate, pitch and vowel lengths.

The second model, the word-based classifier, is also an LSTM network that consumes one word at a time, the current best partial transcript that the ASR system is hypothesizing (note: this partial hypothesis can change over time as the ASR system receives more and more chunks of audio). Similar to the acoustic classifier, the word-based classifier is trained to output a probability indicating whether the current observation (i.e., sequence of words) likely constitutes a complete user query. The intuition is that not only acoustics but also the spoken content, i.e. words, carry information on whether a speech segment is final or not. For example, the fact that the transcript “play music by” ends in a preposition makes it likely that the user has something else to add.

In addition to these two classifiers, a third model component comes into play: meta-features emitted by the ASR decoder. These meta-features describe for how long (if at all) the ASR decoder is running “idle.” In other words, how meaningful are the incoming audio chunks (actual content vs. silence/noise)?

Finally, the above-mentioned classification layer (again a neural network) consumes the individual predictions from the acoustic and the word-based classifier as well as the meta-features from the ASR decoder and outputs a final prediction score (between 0 and 1) indicating whether an end-point should be triggered and a reply to the user initiated.

Paper: "Combining Acoustic Embeddings and Decoding Features for End-of-Utterance Detection in Real-Time Far-Field Speech Recognition Systems"

Acknowledgements: Ariya Rastrow, Chengyuan Ma, Guitang Lan Kyle Goehner, Gautam Tiwari, Shaun Joseph, Bjorn Hoffmeister

About the Author
Roland Maas is an applied-science manager with Alexa Speech.

Related content

Work with us

See more jobs
US, WA, Seattle
Amazon Advertising is one of Amazon's fastest growing and most profitable businesses. As a core product offering within our advertising portfolio, Sponsored Products (SP) helps merchants, retail vendors, and brand owners succeed via native advertising, which grows incremental sales of their products sold through Amazon. The SP team's primary goals are to help shoppers discover new products they love, be the most efficient way for advertisers to meet their business objectives, and build a sustainable business that continuously innovates on behalf of customers. Our products and solutions are strategically important to enable our Retail and Marketplace businesses to drive long-term growth.We deliver billions of ad impressions and millions of clicks and break fresh ground in product and technical innovations every day. We optimize ad placements to match advertiser demand with publisher supply using a combination of machine learning, deep learning, and natural language processing (NLP), query reformulations, big data analytics, and low latency, high-volume systems. We are highly motivated, collaborative and fun-loving, with entrepreneurial drive and bias for action. With a broad mandate to experiment and innovate, we are growing at an unprecedented rate with a seemingly endless range of new opportunities.The Sponsored Sourcing Delivery team owns Ads Searching, Selection and Ads matching systems that involve efficient information retrieval (IR) Search algorithms, query reformulations, Natural language processing, deep-learning algorithms to enable a superior shopper experience and render highly relevant products for shopper’s mission. As Applied Science Manager responsible for Sponsored Sourcing Delivery team you will take ownership of the technical roadmap and delivery of real-time, scalable machine learning models influencing ad selection, relevance and ranking models. You will enable applied scientists to experiment and innovate quickly with a diverse set of models, features and techniques in a high-volume, low-latency environment. The Sponsored search solutions play a key role in the Amazon’s ad serving workflow (selection, ranking and auction) and operate under highly optimized settings viz. scanning billions of documents within milliseconds budget and ensuring high relevance. So the level of quality and reliability are critically important. You’ll raise the bar on software delivery, researching and innovating new matching algorithms and solution quality by investing in Sponsored Products Search features, key initiatives, and technical improvements to optimize for business impact and long-term sustainability.As a Senior Applied Scientist on this team, you will:· Be a technical leader in Machine Learning and drive full life-cycle Machine Learning projects.· Lead technical efforts within this team and across other teams.· Build machine learning models, perform proof-of-concept, experiment, optimize, and deploy your models into production.· Run A/B experiments, gather data, and perform statistical analysis.· Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving.· Work closely with software engineers to assist in productionizing your ML models.· Research new and innovative machine learning approaches.· Recruit Applied Scientists to the team and mentor scientists on the team.Why you will love this opportunity: Amazon is investing heavily in building a world-class advertising business. This team defines and delivers a collection of advertising products that drive discovery and sales. Our solutions generate billions in revenue and drive long-term growth for Amazon’s Retail and Marketplace businesses. We deliver billions of ad impressions, millions of clicks daily, and break fresh ground to create world-class products. We are a highly motivated, collaborative, and fun-loving team with an entrepreneurial spirit - with a broad mandate to experiment and innovate.Impact and Career Growth: You will invent new experiences and influence customer-facing shopping experiences to help suppliers grow their retail business and the auction dynamics that leverage native advertising; this is your opportunity to work within the fastest-growing businesses across all of Amazon! Define a long-term science vision for our advertising business, driven from our customers' needs, translating that direction into specific plans for research and applied scientists, as well as engineering and product teams. This role combines science leadership, organizational ability, technical strength, product focus, and business understanding.Team video https://youtu.be/zD_6Lzw8raEAbout the hiring groupThe Sponsored Sourcing Delivery team helps deliver billions of ad impressions and millions daily clicks daily. Our core charter revolves around building state-of-art machine-learning (ML) and natural-language-processing (NLP) methodologies to improve the search indexing & ranking mechanisms, which will directly improve the advertiser and shopper experience. We’ve been one of the fastest growing teams in Amazon in terms of business impacts launched and momentum continues. We’re a talented team of scientists and engineers working on complex and ambiguous problems, and we have an engineering-driven culture that influences business outcomes.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, CA, Sunnyvale
Amazon is looking for a creative Applied Scientist to tackle some of the most interesting problems on the leading edge of information retrieval (IR) and machine learning (ML) with our Alexa Artificial Intelligence (AI) team. Alexa AI aims to reinvent search and information retrieval for a voice-forward, multi-modal future. We enable customers to interact with unstructured and semi-structured content via a broad range of customer experiences including question answering, summarization, search, and multi-turn dialogues.Job responsibilitiesIf you are looking for an opportunity to develop innovative solutions to deep technical problems having a massive customer impact, this might be the role for you! As an Applied Scientist, you will work with smart, passionate colleagues in a fast-paced environment. You will develop and help deploy novel, scalable algorithms to advance the state-of-the-art in technology areas at the intersection of IR and ML. You will keep up with relevant research in the field of IR and publish your work in top-tier conferences. You will contribute to a multi-year research roadmap, enabling the team to focus on the right technical challenges to delight our customers.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, CA, Sunnyvale
Amazon is looking for a creative Senior Applied Scientist to tackle some of the most interesting problems on the leading edge of Question Answering (QA), information retrieval (IR) and machine learning (ML) with our Alexa Artificial Intelligence (AI) team. Alexa AI aims to reinvent search and information retrieval for a voice-forward, multi-modal future. We enable customers to interact with unstructured and semi-structured content via a broad range of customer experiences including question answering, summarization, search, and multi-turn dialogues.If you are looking for an opportunity to develop innovative solutions to deep technical problems having a massive customer impact, this might be the role for you!About the hiring groupAlexa AI aims to reinvent search and information retrieval for a voice-forward, multi-modal future. We enable customers to interact with unstructured and semi-structured content via a broad range of customer experiences including question answering, summarization, search, and multi-turn dialogues.Job responsibilitiesAs a Senior Applied Scientist with Alexa AI, you will work with smart, passionate colleagues in a fast-paced environment. You will develop and help deploy novel, scalable algorithms to advance the state-of-the-art in technology areas at the intersection of QA, IR and ML. You will keep up with relevant research in the field of NLU & IR and publish your work in top-tier conferences. You will develop and help lead the execution of multi-year research roadmaps, enabling the team to focus on the right technical challenges to delight our customers.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, CA, Virtual Location - California
Amazon’s commitment to The Climate Pledge motivates us to work both inside and outside of our business operations to enact carbon emissions mitigation. Along with the emissions reduction initiatives within our business operations, we have a robust strategy aligned with climate science for tackling climate change outside of our business, beginning with nature-based solutions. As we continue to develop and innovate, Amazon is seeking an experienced Research Scientist to help us identify, evaluate, and guide research efforts in nature-based solutions as well as emerging areas. The ideal candidate will have a deep understanding of carbon cycles and be able to evaluate projects and initiatives across a wide range of natural and technological climate mitigation measures from a first-principles perspective. They will have expertise in one or more types of climate solutions, but more importantly will understand the broad field of solutions.The successful candidate will be part of the team executing on Amazon’s commitment to The Climate Pledge. They will need to work with others to create a system to evaluate nature-based and technological climate solution projects, and make recommendations to senior leadership. This will require strong writing skills and an ability to translate technical material for a general audience.Key Responsibilities:· Evaluate nature-based and technological climate solution projects using a scientifically rigorous first-principles approach.· Evaluate project and research proposals.· Collaborate with internal and external teams to scope, execute, and evaluate highly technical initiatives related to nature-based and technological climate solution projects.· Translate findings into reports and presentations that can be shared internally and externally.· Respond to time-critical questions from multiple business teams and communicate professionally with senior business leaders.Inclusive Team CultureHere at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have 12 affinity groups (employee resource groups) with more than 87,000 employees across hundreds of chapters around the world. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which reminds team members to seek diverse perspectives, learn and be curious, and earn trust.FlexibilityIt isn’t about which hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We offer flexibility and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthWe care about your career growth too. Whether your goals are to explore new technologies, take on bigger opportunities, or get to the next level, we'll help you get there. Our business is growing fast and our people will grow with it.
US, VA, Arlington
This new role in the ES Tech will establish world class data science/business intelligence, analytics and reporting for Amazonians as part of building the Personalization Engine for myHR. This key role will work closely with internal partners to assist in developing and managing solutions for ES Tech.Core Responsibilities:· Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.· Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.· Leverage big data to explore and introduce areas of analytics and technologies.· Analyze data to identify opportunities to impact populations.· Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.· Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.· Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.· Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools.
US, WA, Seattle
Are you seeking an environment where you can drive innovation? The Consumer Finance Science and Analytics (CFSA) team's mission is to inject data science, econometrics, and advanced analytics into traditional financial analytics. We harness science, technology, and financial analytics to crack Consumer Finance’s toughest challenges and power smart decision-making throughout the organization. We are data leaders who identify and deliver today's actionable scientific analyses and recommendations, and tomorrow’s durable frameworks and software.We are looking for an outstanding economist to drive causal attribution initiatives throughout WW Consumer Finance. You will develop core science-based methodologies and build scalable models to improve financial decision making and planning. You will work on new, transformative initiatives, and you will build new econometric models from the ground up. You will help build an advanced causal attribution framework measuring the downstream impact of clusters of selection. This framework will be used by senior leadership to take actions in order to drive profitability improvements.We prize creative problem solvers with the ability to draw on an expansive methodological toolkit to transform financial decision-making through economics. The ideal candidate combines econometric acumen with strong business judgment. You have versatile modeling skills and are comfortable owning and extracting insights from data. You are excited to learn from and alongside seasoned analysts, scientists, engineers, economists, and business leaders. You are an excellent communicator and effectively translate technical findings into business action.
US, CA, San Diego
Amazon Web Services (AWS) Professional Services team is looking for a Practice Manager in the AI Global Services Practice with a successful history of delivering best-in-class AI/ML solutions, managing world-class talent, and possessing the drive and experience to scale both to effectively meet the needs of our customers.The Practice Manager will build a working relationship with their sales, solution architects, and professional services counterparts. The Practice Manager will also have a team of 8-12 direct reports that are data scientists to develop a long-term AI (Artificial Intelligence) /ML (Machine Learning) strategy and execution plan within their geographic regions with other AWS Professional Services colleauges. This individual is a trusted adviser for our enterprise customers and requires the skills to excel at all aspects of business development, people management, relationship development, delivery of AI solutions and program management in their accounts, following a player/coach model.RESPONSIBILITIES• Hiring, developing and retaining top talent.• Engage with commercial enterprise customers to understand their business drivers and application portfolio.• Development of long term AI/ML strategy for our customers• Identification and development of specific AI opportunities and supporting business cases.• Mitigation of delivery risks and issues.• Overseeing delivery of AI projects, ensuring high quality delivery.• Act as single person of contact for Customer executives, developing deep, trustful relations.• Educate customers on AWS AI/ML services and translate those into a clear business value proposition.• Envision and inspire customers, on the potential of ML to help their business.• Coaching Customer and Partner teams to be self-sufficientInclusive Team CultureHere at AWS, we embrace our differences. We are committed to furthering our culture of inclusion. We have thirteen employee-led affinity groups, reaching 85,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.Work/Life BalanceOur team puts a high value on work-life balance. Striking a healthy balance between your personal and professional life is crucial to your happiness and success here. We are a customer-obsessed organization—leaders start with the customer and work backwards. They work vigorously to earn and keep customer trust.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded professional and enable them to take on more complex tasks in the future.
US, CA, Sunnyvale
Amazon Device AI team is looking for a Principal Applied Scientist to lead the development of computer vision algorithm on the Edge. In this role, you will be the leader of our passionate, talented, and inventive scientists, to develop industry-leading Computer Vision (CV), and drive them successfully to production for the benefit of millions of Amazon Devices users.You will provide thought leadership to scientists and engineers to help invent and implement computer vision and machine learning algorithms. This is a unique, high visibility opportunity for a leader who wants to have business impact, and dive deep into computer vision problems. We are particularly interested in candidates with experience productizing edge-based computer vision systems.As a Principal Applied Scientist, you bring structure to ambiguous business problems and use science, logic, and practical experience to decompose them into straightforward, scalable solutions. You set the standard for scientific excellence and make decisions that affect the way we build and integrate algorithms. Your solutions are exemplary in terms of algorithm design, clarity, model structure, efficiency, and extensibility. You tackle intrinsically hard problems; you're interested in learning; and you acquire skills and expertise as needed.The ideal candidate is a strong, creative and highly-motivated Scientist with hands-on experience in leading multiple research and engineering initiatives. You balance technical leadership with strong business judgment to make the right decisions about technology, tools, and methodologies.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
CA, ON, Toronto
Amazon's Sponsored Products advertising business is one of the fastest growing areas in the company. Have you ever wondered what happens behind that “Sponsored” label you see on Amazon? The Sponsored Products Marketplace team creates and optimizes the systems that match advertiser demand (ads) with page supply (placements) using a combination of data-driven product innovation, machine learning, big data analytics, and low latency/high-volume engineering. By the time organic search results are ready, we've processed all of the candidate ads and determined which ones are delivered to the page. We do that billions of times per day, resulting in millions of engagements with products that otherwise might not have been seen by shoppers. The business and technical challenges are significant. Fortunately, we have a broad mandate to experiment and innovate, and a seemingly endless range of new opportunities to build a big, sustainable business that helps Amazon continuously delight all of our customers.We're looking for an innovative and customer-obsessed Applied Scientist who can help us take our products to the next level of quality and performance by creating state-of-the-art models to improve our ability to predict entity relationships, forecast the impact of advertiser actions, and optimize ad selection for different contexts. We embrace leaders with a startup mentality -- those who have a disruptive yet clear mission and purpose, an unambiguous owner's mindset, and a relentless obsession for delivering amazing products.As an Applied Scientist on the Keywords Targeting team, you will work alongside business leaders, other scientists, and software engineers to deliver recommenders and forecasters based on ML, DL, and RL from idea to production. You will be responsible for bridging the experimental domain with the production domain by building robust and efficient computational pipelines to scale up models, keeping the models fresh, and ensuring that real-world corner cases are handled correctly. You'll own significant products and features from inception through launch, and will work with Product Managers, other Scientists, and Engineers to make your efforts wildly successful. As a primary science contributor for our team, you will be providing input to strategic decision making on topics such as program direction/vision, roadmap, and staffing. If this sounds like your sort of challenge, read on.Characteristics indicative of success in this role:· Highly analytical: You solve problems in ways that can be backed up with verifiable data. You focus on driving processes, tools, and statistical methods which support rational decision-making.· Technically fearless: You aren't satisfied by performing 'as expected' and push the limits past conventional boundaries. Your dial goes to '11'.· Engaged by ambiguity: You're able to explore new problem spaces with unique constraints and non-obvious solutions.· Team obsessed individual contributor: You help grow your team members to achieve outstanding results. You've learned that big plans generally involve collaboration and great communications.· Quality obsessed: You recognize that professional scientists build high quality model development and evaluation frameworks to ensure that their models can provably meet launch criteria, or efficiently iterate in the framework until they do.· Humbitious: You’re ambitious, yet humble. You recognize that there’s always opportunity for improvement. You use introspection and feedback from teammates and peers to raise the bar.Primary Responsibilities:· Apply machine learning and analytical techniques to create scalable solutions for business problems· Work closely with software engineering and product teams across the organization to drive model implementations and new feature creations· Work closely with business stakeholders to identify opportunities for current model improvements and new models to significantly benefit the business bottom-line· Collaborate with scientists within the Ads organization as well as other parts of Amazon to share learnings move the state-of-the-art forward· Establish scalable, efficient, automated processes for data analyses, model development, model validation and model implementation· Research and implement novel machine learning and statistical approachImpact and Career GrowthYou will invent new shopper and advertiser experiences, and accelerate the pace of Machine Learning and Optimization.Influence customer facing shopping experiences to helping suppliers grow their retail business and the auction dynamics that leverage native advertising, this role will be powering the engine of one the fastest growing businesses at Amazon.Define science objectives for our ad marketplace, driven fundamentally from the needs of our customers, translating that direction into specific plans for research and applied scientists, as well as engineering and product teams.This is a role that combines science, organizational ability, technical strength, product focus and business understanding.Why you love this opportunityAmazon is investing heavily in building a world class advertising business and we are responsible for defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products. We are highly motivated, collaborative and fun-loving with an entrepreneurial spirit and bias for action. With a broad mandate to experiment and innovate, we are growing at an unprecedented rate with a seemingly endless range of new opportunities.Team video ~ https://youtu.be/zD_6Lzw8raE
GB, London
Amazon opened its virtual doors in 1995 and strives to be the world’s most customer-centric company, where customers can find and discover anything they might want to buy online.The Amazon Logistics team is offering positions to creative big thinkers who are passionate about using data to direct decision making and solve complex and large-scale challenges. We are looking for individuals with a strong interest in improving one of the world’s most complex logistic systems. As part of the Amazon Logistics team, we design and build systems that support planning decisions, measure and manage the last mile transportation, real estate investments, and resource planning.As a Data Scientist, your main focus will be to perform analysis, build metrics, synthesize information, identify business opportunities, provide project direction, and communicate business and technical requirements within the team and across stakeholder groups. You are indispensable and own the quantification of business opportunities and identification of project direction prioritizing projects based on greatest return on investment. You consider the needs of day-to-day operations and insist on the standards required to build the network of tomorrow. Your job will straddle day-to-day decisions and strategic vision, you will assist in defining trade-offs and quantifying opportunities for a variety of projects. You will learn current processes, build metrics, educate diverse stakeholder groups, assist science groups in initial solution design, and audit all model implementation. A successful candidate in this position will have a background in communicating across significant differences, prioritizing competing requests, and quantifying decisions made. You will balance the trade-offs between customer experience, network speed, and cost, to measurably improve the network in a 3 to 6-month time-frame.This position requires superior analytic thinkers, who are able to quickly approach large ambiguous problems and apply their technical and statistical knowledge to identify opportunities for further research. The ideal candidate will demonstrate a deep understanding of identifying meaningful key performance indicators and building actionable metrics. This candidate is passionate about providing insights that drive larger initiatives and sees the undeniable value of a good metric. You should be able to independently mine and analyze data, and be able to use any necessary programming and statistical analysis software to do so. Successful candidates must thrive in fast-paced environments which encourage collaborative and creative problem solving and be able to measure and estimate risks.About our rewardsWe’ll expect you to go the extra mile, but we’ll also make sure you’re well rewarded. As well as a competitive salary and stock units, we offer a whole host of other benefits, including an employee discount.There are other, more intangible rewards too. Like our commitment to your development, a refreshing lack of hierarchy, the chance to work with some of the brightest minds in the industry, plenty of team spirit and an informal atmosphere – suits and ties are few and far between.Amazon is an equal opportunities employer. We believe passionately that employing a diverse workforce is central to our success. We make recruiting decisions based on your experience and skills. We value your passion to discover, invent, simplify and build. We welcome applications from all members of society irrespective of age, sex, disability, sexual orientation, race, religion or belief.
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in technology to solve real-world problems. As a Data Scientist at the intersection of machine learning and the life sciences, you will participate in developing exciting products for customers. Our team rewards intellectual curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the cutting edge of both academic and applied research in this product area, you have the opportunity to work together with a diverse and talented team of scientists, engineers, and product managers and collaborate with others teams.Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.Work/life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in technology to solve real-world problems. As a Research Scientist, you will work with a unique and gifted team developing exciting products for consumers and collaborate with cross-functional teams. Our team rewards intellectual curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the cutting edge of both academic and applied research in this product area, you have the opportunity to work together with some of the most talented scientists, engineers, and product managers.Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.Work/life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in technology to solve real-world problems. As a Research Scientist, you will work with a unique and gifted team developing exciting products for consumers and collaborate with cross-functional teams. Our team rewards intellectual curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the cutting edge of both academic and applied research in this product area, you have the opportunity to work together with some of the most talented scientists, engineers, and product managers.Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.Work/life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, VA, Arlington
This is a Science Leadership role based in our brand new Arlington, Virginia HQ2 campus!!The Advertising Supply & Monetization team determines the display ads shown to Amazon shoppers, and is responsible for delivering an engaging, relevant and personalized ad experience. We optimize entire pages of retail and advertising content in near real-time for millions of shoppers each day, maximizing the long-term value that display advertising creates for Amazon.As a Sr. Applied Scientist, your core efforts will involve leading the evolution of real-time pricing and valuation models for advertising in the context of delivering a highly personalized content experience on retail shopping pages. You will invent measures to quantify the impact on shopping from changes in ad quality, relevance, and the general user experience with ads. You will deploy services to help us better optimize against these measures, and identify opportunities to improve bidding strategies into the Amazon auction to deliver impact to Amazon’s shopper and advertiser customers.This is a unique, high visibility opportunity for a talented, motivated individual to deliver direct impact to Amazon shoppers, have business impact, and dive deep into high-scale low latency problems at the cutting edge of machine learning, optimization and economics. As a Sr. Applied Scientist on the Advertising Supply & Monetization team, you will work closely with scientists, economists, engineers and business leaders to translate business and functional requirements into concrete deliverables, including design, development and testing. You will act as a thought leader and forward thinker on the team anticipating obstacles to success and helping us avoid common failure modes. You will also contribute to hiring and coaching junior scientists and partner with engineering leaders to build efficient scalable systems.This role offers a compelling mix of contemporary research problems that are unique to Amazon based on the interplay between retail and advertising, scale and richness of data sets, emphasis on user experience and relevance, and complexity introduced by concurrent experimentation across teams. In addition, you will deliver significant customer and business impact by shaping the future of the Amazon shopping experience and delivering growth to the advertising business.Why you will love this opportunity: Amazon is investing heavily in building a world-class advertising business. This team defines and delivers a collection of advertising products that drive discovery and sales. Our solutions generate billions in revenue and drive long-term growth for Amazon’s Retail and Marketplace businesses. We deliver billions of ad impressions, millions of clicks daily, and break fresh ground to create world-class products. We are a highly motivated, collaborative, and fun-loving team with an entrepreneurial spirit - with a broad mandate to experiment and innovate.Impact and Career Growth: You will invent new experiences and influence customer-facing shopping experiences to help suppliers grow their retail business and the auction dynamics that leverage native advertising; this is your opportunity to work within the fastest-growing businesses across all of Amazon! Define a long-term science vision for our advertising business, driven from our customers' needs, translating that direction into specific plans for research and applied scientists, as well as engineering and product teams. This role combines science leadership, organizational ability, technical strength, product focus, and business understanding.Team video https://youtu.be/zD_6Lzw8raE
GB, Cambridge
Do you want to work on some of the most innovative Text-to-Speech technology in the industry? Well, you’ve come to the right place.We are looking for a passionate, talented, and inventive Machine Learning Scientist with a strong background in Machine/Deep Learning/NLP/Speech and Software Development to help build industry-leading Speech and Language technology. Our mission is to push the envelope in Text-to-Speech (TTS) in order to provide the best-possible experience for our customers. Your role is to leverage your strong background in Computer Science and Machine Learning to help build the next generation of our synthetic voices used by millions of customers every day.A day in the lifeNo two days are the same as a Applied Scientist in TTS Research!You will be working in a dynamic, fast-moving environment. You’ll be developing new Deep learning models to improve the quality of our speech models, running experiments and writing papers and patents or making prototype solutions production ready.About the hiring groupThis role sits with TTS, and the goal of the team is to create natural, friendly and emotional voices for Alexa.Job responsibilitiesAs an Machine Learning Scientist on our team you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art in speech synthesis. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to build Machine Learning models for their application in speech synthesis.This role requires a pragmatic technical leader comfortable with ambiguity, capable of summarizing complex data and models through clear visual and written explanations.The ideal candidate will have experience with machine learning models and their application in AI systems. We are particularly interested in experience applying natural language processing, deep learning, and speech generation at scale. Additionally, we are seeking candidates with strong interest in applied sciences and engineering, creativity, curiosity, and great judgment.Amazon is an equal opportunities employer. We believe passionately that employing a diverse workforce is central to our success. We make recruiting decisions based on your experience and skills. We value your passion to discover, invent, simplify and build. Protecting your privacy and the security of your data is a longstanding top priority for Amazon. Please consult our Privacy Notice to know more about how we collect, use and transfer the personal data of our candidates.
IN, KA, Bangalore
The Amazonian Experience and Technology (AET) team is looking for a passionate Applied Scientist with experience in Natural Language Processing to help us fulfill our goal of becoming the most scientific people experience and technology organization in the world. In this role, you will work with service owners across the globe to help automate manual processes to help us solve employee problems faster and more efficiently. You will come across challenging problems, using data to solve issues such as contact classification, automatic translation, intelligent routing, and text autocompletion that will be used by employees and AET agents to improve the experience of Amazonians reaching out to HR.About the hiring groupThe Data and Analytics Services, Research and Applied Science team provides rigorous scientific support to business partners across the globe within the Amazonian Experience and Technology organization. Our goal is to make operations as efficient as possible by leveraging science to make sure the experience of Amazonians when contacting HR is as frustration free as possible. In this team, you will work with Economists, Applied Scientists, Data Scientists and Software Development Engineers to help solve complicated problems for Amazon's ever growing employee population.Job responsibilities· Analyze data and metrics generated by Amazonian interactions with Human Resources to find opportunities to improve our services.· Design, build, and deploy effective and innovative Machine Learning and Natural Language solutions to improve various components of our processes, like contact routing, case classification, translation, and fraud detection.· Evaluate the proposed solutions via offline benchmark tests as well as online A/B tests in production.· Publish and present your work at internal and external scientific venues
US, NY, New York
Are you passionate about machine learning? Do you want to drive the innovation behind real-world recommendation systems? Do you want to impact what is shown to Amazon customers across the website by innovating with Amazon scale data? We are looking for a passionate person who can build a team and drive an innovation roadmap as part of Amazon’s centralized content recommendation and personalization service. The person will have high exposure within Amazon and their work will impact all Amazon customers. They will need to negotiate effectively and have good written and oral communication skills.When leading this team, you will be required to :· drive scientist roadmap and determine which areas of research to invest· hire and develop the best· effectively communicate complicated machine learnings concepts to multiple partners.· drive big picture innovations with clear roadmaps for intermediate delivery· identify when to leverage existing technology versus innovate a new technology· work closely with partners to identify problems from the customer's perspective· incorporate subject matter expertise from across the company into our machine learning systems
US, VA, Arlington
***This role is open to the following locations: Arlington VA, Austin TX, Las Vegas NV, or Boston MA***This new role in the Amazon Benefits Department will establish world class data science/business intelligence, analytics and reporting for the Amazon international benefit plans. This key role will work closely with internal and external partners to assist in developing and managing health care and population health management solutions for the Amazon Benefits Department. The Data Scientist will be expected to have a deep understanding of health plans, and will analyze data to help identify opportunities to improve employee wellbeing and health care outcomes, while reducing medical expenditures.Core Responsibilities:· Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.· Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.· Leverage data to explore and introduce areas of health care analytics and technologies.· Analyze data to identify opportunities to impact populations.· Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.· Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.· Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.· Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools.
US, WA, Seattle
Prime Video is shaping the future of digital video entertainment. Our vision is to provide the most comprehensive global video service that customers choose first and spend the most time engaged with. Our Amazon Prime subscription streaming service provides a broad selection of shows, movies and live sports included with customers’ subscription to Amazon Prime. With TVOD (Rent or Buy) and Channels (subscribe to premium channels such as HBO or Starz), we augment our proposition by giving customers immediate access to the broadest selection of video content available anywhere (nearly 200,000 titles), and we drive monetization opportunities for our business.The Worldwide Marketplace Science Team within Amazon Prime Video builds commercial optimization tools for our TVOD and Channels businesses. In this role, you will invent science and systems for TVOD and Channels, including ML-based pricing, personalized promotions, and subscription bundles, among others. You will work with a team of economists and machine learning scientists to design commercial products, and you will work with technology teams to productize and maintain the associated solutions.We are looking for the next outstanding data scientist to join our interdisciplinary team of analysts, data scientists, economists, and engineers. The ideal candidate combines data-science acumen with strong business judgment. You have versatile modeling skills and are comfortable extracting insights from observational and experimental data. You translate insights into action through proofs-of-concept and partnerships with engineers to productionize. You are excited to learn from and alongside seasoned analysts, scientists, engineers, and business leaders. You are an excellent communicator and effectively translate business ideas and technical findings into business action (and customer delight).Key Responsibilitieso Partner with business, finance, and tech teams to build models and productized science for TVOD and Channels, such as:o Targeting and personalizing promotionso Optimize content lifecycling and pricing across lines of businesso Valuing portfolios of TVOD contento Serve as a science / strategy advisor to global TVOD and Channels businesses
US, WA, Seattle
Prime Video is shaping the future of digital video entertainment. Our vision is to provide the most comprehensive global video service that customers choose first and spend the most time engaged with. Our Amazon Prime subscription streaming service provides a broad selection of shows, movies and live sports included with customers’ subscription to Amazon Prime. With TVOD (Rent or Buy) and Channels (subscribe to premium channels such as HBO or Starz), we augment our proposition by giving customers immediate access to the broadest selection of video content available anywhere (nearly 200,000 titles), and we drive monetization opportunities for our business.Worldwide Marketplace Science (within Amazon Prime Video) builds production systems to transform how our TVOD and Channels businesses grow and monetize. In this role, you will invent science and systems for TVOD and Channels, including ML-based pricing, personalized promotions, and customized subscription bundles, among others. You will work with a team of economists and machine learning scientists to design customer-facing products, and you will work with technology teams to productize and maintain the associated solutions.We are looking for the next outstanding data scientist to join our interdisciplinary team of analysts, data scientists, economists, and engineers. The ideal candidate combines data-science acumen with strong business judgment. You have versatile modeling skills and are comfortable extracting insights from observational and experimental data. You translate insights into action through proofs-of-concept and partnerships with engineers to productionize. You are excited to learn from and alongside seasoned analysts, scientists, engineers, and business leaders. You are an excellent communicator and effectively translate business ideas and technical findings into business action (and customer delight).Key Responsibilities· Research, develop, and implement scalable solutions for targeted and personalized promotions, recommended actions for studio partners, and more!· Coordinate with business, finance, and tech teams to expand understanding of what is possible and ensure focus on the right problems· Collaborate with tech and engineering teams to develop and optimize production systems· Work with other scientists to raise the science bar across Prime Video