Alexa Scientists Present Two New Techniques That Improve Wake Word Performance

The Amazon Echo is a hands-free smart home speaker you control with your voice. The first important step in enabling a delightful customer experience with an Echo or other Alexa-enabled device is wake word detection, so accurate detection of “Alexa” or substitute wake words is critical. It is challenging to build a wake word system with low error rates when there are limited computation resources on the device and it's in the presence of background noise such as speech or music.

Next week, at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018, we are presenting two new techniques that improve on-device wake word detection performance:

  1. A new deep neural network (DNN) architecture for training a speech feature directly from raw audio input; and
  2. A novel background noise modeling method using monophone-based sound units that can take richer information into account.

In the first paper, we focus on improving the DNN-Hidden Markov Model (HMM) system by training a feature extraction DNN from raw audio rather than handcrafting a speech feature traditionally used in speech recognition. In the second paper, we present a new wake word system that comprises a two-stage classifier and show how wake word performance can be improved by incorporating richer phone (classes of sound) contexts into the two-stage system.

Time Delayed Bottleneck Highway Networks

The illustration below contrasts a conventional DNN architecture to our new DNN structure. A main difference between the two is that our new system replaces a handcrafted log-mel filter bank energy (LFBE) front-end with a trainable front-end DNN. By directly modeling raw audio rather than LFBE, we can learn novel features of the target wake word and optimize our classifier for improved performance. Except for the discrete Fourier transform (DFT), this approach is wholly data-driven. We apply the highway network to direct audio modeling to alleviate the hard optimization problem caused by a deep network structure. Furthermore, we efficiently reduce the large dimension of an input vector with a bottleneck layer followed by a time-delayed window.

Time Delayed Bottleneck Highway Networks

The graph below shows that our time-delayed bottleneck highway network with the DFT input significantly reduces a range of false alarm rates (FAR), yielding approximately a 20 percent relative improvement in the area under the curve (AUC), a common measure of machine-learning model accuracy. It is also clear from our work that a larger amount of training data would improve wake word detection performance.

Contrast of a conventional and our new wake word system
Contrast of a conventional and our new wake word system

Monophone-Based Background Modeling

In this paper, we introduce a two-stage on-device wake word detection system based on DNN acoustic modeling, propose a new approach for modeling background noise using monophone-based sound units, and present how richer information can be extracted from the monophone sound units to improve wake word accuracy.

An overview of the two-stage wake word system
An overview of the two-stage wake word system

With this new approach, we achieved about a 16 percent relative reduction in instances where Alexa doesn’t respond to the wake word (false rejection rates, or FRR) and about a 37 percent relative reduction in instances when Alexa mistakenly believes she’s heard the wake word, or false alarm rates (FAR). Moreover, when we introduce a second-stage classifier that extracts monophone units for final wake word detection, we reduce FAR by about 67 percent utilizing very few additional computational resources.

Below are the papers we’re presenting at ICASSP next week. Although each method is presented as separate work, both techniques can of course be combined to achieve better wake word performance. That will be the focus of our future work.

Papers:
"Time-Delayed Bottleneck Highway Networks Using A DFT Feature For Keyword Spotting"
"Monophone-based Background Modeling For Two-Stage On-Device Wake Word Detection"

Acknowledgements: Kenichi Kumatani, Sankaran Panchapagesan, Jinxi Guo, Ming Sun, Anirudh Raju, Jiacheng Gu, Ryan Thomas, Nikko Ström, Shiv Naga Prasad Vitaladevuni, Bjorn Hoffmeister, Arindam Mandal, as well as the entire Wake Word team for supporting this work.

About the Author
Minhua Wu is an applied scientist in the Alexa Speech group.

Related content

View from space of a connected network around planet Earth representing the Internet of Things.
Get more from Amazon Science
Sign up for our monthly newsletter

Work with us

See More Jobs
US, WA, Seattle
Amazon’s Sustainability organization points Amazon’s innovative culture at environmental and social impacts with enormous scale. We consider the full lifecycle of our impact, from supply chain to customer experience, operational efficiency to waste diversion. We take action to improve the impact Amazon has on the environment, looking for wins that are good for our customers and our business as well. Sustainability Science and Innovation is a team of environmental and social research scientists and product managers answering core sustainability questions for the larger organization and working across the company to develop solutions to long term environmental and social hotspots.The Role:A Research Scientist at Amazon applies data science, subject matter expertise, and business acumen to deliver results at scale. As a Research Scientist, you will be responsible for conducting assessments of environmental and social issues across Amazon, evaluating the sustainability impacts of supply chains, from manufacturing, to transportation, to consumer use, to end-of-life. The ideal candidate will have industry experience conducting life cycle assessments (LCAs) of products and services, and detailed knowledge of manufacturing, design, development, and/or sourcing. This candidate will also possess excellent communication, negotiation and influencing skills to drive consensus across multiple stakeholders.The successful candidate must have strong analytical skills and the ability to apply systems thinking to complex, fast moving problems. The candidate should be comfortable working with imperfect data, identifying sources of uncertainty, and finding public data to fill the gaps where needed. The candidate should have familiarity with LCA methods and applications. The successful candidate will work under the direction of senior business leaders, but will act as a Subject Matter Expert, leading research and building data analytics and models at scale. Amazon’s culture encourages innovation, and the candidate should be comfortable working in cold start scenarios in order to push the envelope on the hard to solve environmental and social issues.Key Responsibilities:· Manage sustainability-related research projects through all stages: ideation, modeling, data collection, data analysis, data visualization, and reporting.· Develop tools and methods to harvest and continuously update data to provide sustainability insights at scale.· Respond to time critical questions from multiple business teams.· Professionally communicate to senior business leaders.· Work closely with software engineering teams to drive real-time model implementations and new feature creations.· Lead the early investigative / inception phase of strategic sustainability initiatives and effectively influence, negotiate, and communicate with stakeholders to enable hand off of those projects for implementation.
US, CA, Sunnyvale
The Amazon Alexa Speech Org is looking for entrepreneurial, innovative individuals who thrives on solving tough problems. We need people who are passionate about innovating on behalf of customers, who demonstrate a high sense of ownership, and who want to have fun while they make history. An ideal candidate for Data Scientist at Alexa should have strong data mining and modeling skills and is comfortable working from concept to execution to completion. The candidate will be an individual contributor who is comfortable with ambiguity and able to successfully drive projects to completion. In addition to the modeling and technical skills, the candidate should possess strong written and verbal communication skills, strong focus on internal customers and high intellectual curiosity with the ability to learn new concepts/frameworks, algorithms, and technology rapidly as changes arise.Data Scientists at Alexa will design, evangelize, and implement solutions to address complex, business questions using advanced statistical techniques, experimentation, and big data. You will be interacting with science and research teams to define metrics that drive key business decisions, and working with program managers, quality assurance engineers and software developers, to develop data pipelines, build tools to drive continuous experimentation to generate data set, conduct statistical analyses, and provide actionable insights for business decisions. Key responsibilities:· Adopt best practices and implement strategies for data audit, data integrity, and validation· Utilize code (Python, R, Scala, etc.) for analyzing data and building statistical models to solve specific business problems· Execute end to end insights projects include data collecting, data cleaning, exploratory analysis, model selection, model evaluation, and interpreting results· Apply or design highly innovative models for predictive learning, content ranking, and anomaly detection· Analyze and extract relevant information from large amounts of historical data to help automate and optimize key processes· Analyze key metrics to uncover trends and root causes of issues· Communicate verbally and in writing to business customers and leadership team with various levels of technical knowledge, and share insights and recommendations
GB, London
The EU Workforce Staffing Analytics team is responsible for our hourly workforce: Who do we hire? How should we hire them? How do we make sure the right candidate gets the right role at the right time, and how do we do this efficiently? As Amazon moves toward free one day shipping for prime customers, and as we continue to scale, answering these questions will have material impact on the business, and on the experience our candidates have.Here’s where you come in:What is the role? As a Data Scientist in Workforce Staffing, your work is focused on research programs to deeply understand the people that make up our hourly workforce. You understand that even when hiring hundreds of thousands of hourly associates across multiple types of roles and businesses, the experience of each candidate matters.You use your deep expertise in statistics (regressions, multilevel models, structural equation models, etc.), and data collection in a variety of settings (e.g., field studies, surveys, existing large data sets) to define and answer nebulous problems. You leverage your quantitative background to develop and test theoretical frameworks and design experiments. You design, deployment, and conduct analysis of our EU candidate research activities, using experimental, quasi-experimental, and RCT methods. You relentlessly obsess over understanding our candidates and what attracts them to Amazon. You work with colleagues across Research, Data Science, Business Intelligence and related teams to enable Amazon find and hire the right candidates for the right roles at an unprecedented scale.This will be a highly visible role across multiple key deliverables for our EU organization. If you are passionate and curious about data, obsess over customers, love questioning the status quo, and want to make the world a better place, let’s chat.
US, WA, Seattle
At Amazon, we strive every day to be Earth’s most customer centric company. Do you want to join an innovative team who uses traditional machine learning, deep learning, and natural language processing techniques to insert intelligence into our processes to help provide world class support to our global network of selling partners in an efficient and scalable manner? Are you interested in helping our associates by streamlining their processes and offering them fast, efficient routes and tools to case resolution? Amazon Partner Solutions And Support Machine Learning team is looking for an Applied Scientist to build efficient, flexible, and scalable machine learning and general applied science solutions that help us solve our most challenging problems. In this role, you will have ownership of the end-to-end development of solutions to complex problems and you’ll play an integral role in strategic decision-making. You will also work closely with engineers to build ML pipelines, platforms and solutions that solve problems of intent classification, automation, and workforce optimization.
US, WA, Seattle
Prime Video is disrupting traditional media with an ever-increasing selection of movies, TV shows, Emmy Award-winning original content, add-on subscriptions including HBO and Showtime, and live events like Thursday Night Football and Major League Baseball. We are a premier provider of digital entertainment worldwide and we continue to grow very quickly! We need your passion, innovative ideas, and creativity to help continue to deliver on our ambitious goals.Do you want to join an innovative team of scientists who use machine learning and statistical techniques to help Amazon provide the best customer experience by protecting Amazon customers from harmful content ? Do you want to build advanced algorithmic systems that help millions of customer every day? Are you excited by the prospect of analyzing and modeling terabytes of data and creating state-of-the-art algorithms to solve real world problems? Do you like to innovate and simplify? If yes, then you may be a great fit to join our Amazon Prime Video team.We are expanding our scene understanding team to drive compliance automation and exceptional customer experience using machine learning, computer vision, audio processing, and natural language understanding. Automation of video understanding at scale is our mission and passion. We need to solve problems across many cultures and languages. we have a huge amount of human-labelled data, and operation team to generate labels across many languages. Our team innovates, with many novel patents, inventions, and papers in the motion picture and television industry. We are highly motivated to extend the state of the art.As an applied scientist, you will apply your knowledge of deep learning to concrete problems that have broad cross-organizational, global, and technology impact. Your work will focus on training and evaluating models and deploying them to production where we continuously monitor and evaluate. You will work on large engineering efforts that solve significantly complex problems facing global customers. You will be trusted to operate with independence and are often assigned to focus on areas with significant impact on audience satisfaction. You must be equally comfortable digging in to customer requirements as you are drilling into design with development teams and developing production ready learning models. You consistently bring strong, data-driven business and technical judgment to decisions. This is a greenfield with no "off-the-shelf algorithms" that can perform the job. We experiment a lot and it is a must to learn and be curios. You will be encouraged to see the big picture, be innovative, and positively impact millions of customersYou'll work with experienced managers who'll care for you. We'll guide you on your career growth path and there's no shortage of technical challenges.You will work with internal and external stakeholders, cross-functional partners, and end-users around the world at all levels. Our team makes a big impact because nothing is more important to us than pleasing our customers, continually earning their trust, and thinking long term. You are empowered to bring new technologies and deep learning approaches to your solutions.We embrace the challenges of a fast paced market and evolving technologies, paving the way to universal availability of content. You will be encouraged to see the big picture, be innovative, and positively impact millions of customers. This is a young and evolving business where creativity and drive will have a lasting impact on the way video is enjoyed worldwide.
US, CA, Hawthorne
We are looking for an experienced and motivated Data Scientist with proven abilities to build and manage modeling projects, identify data requirements as well as build methodology and tools that are statistically grounded.You should be an expert in the areas of data science, optimization, machine learning and statistics, and are comfortable facilitating ideation and working from concept through execution. As a member of the Ring Failure Analysis team, your primary responsibilities include supporting investigations to determine root cause of failures in consumer electronics. You will work with other subject matter experts in video, motion sensing, power and communication technologies to help improve products and the customer experience. You will be required to multi-task and prioritize work to meet schedule and cost needs.The ideal candidate should have a demonstrated ability to think strategically and analytically about business, product, and technical challenges. This role requires a high level of comfort navigating ambiguity, and a keen sense of ownership and drive to deliver results.RESPONSIBILITIES· Responsible for identifying and researching failures at the system level to improve product yield, quality and reliability.· Work with functional teams as needed to understand device issues.· Articulate conclusions to the team and advocate for appropriate action.· Develop new diagnostic tools or tests and more efficient FA techniques.· Interface with other technology teams to extract, transform, and load data from a wide variety of data sources using SQL· Interface with business customers, gathering requirements and delivering complete data structures· Drive well-formed experiment design and measurement plans.· Monitor existing processes, create and automate new and existing reporting and work across the organization to make actionable decisions available to stakeholders.· Assist with ongoing FA investigations by providing metrics as well as statistical analysis.
US, CA, San Diego
At Amazon, we strive every day to be Earth’s most customer centric company. Amazon Perfect Order Experience (POE) team works to ensure that customers can buy with confidence on Amazon. We develop and implement large scale machine learning solutions to protect the buying experience on Amazon while minimizing friction for our selling partners. We develop state-of-the art Natural Language Processing models to detect negative customer experience in real-time and build an ever-evolving risk monitoring system to proactive protect customer trust.We are looking for a Sr. Applied Scientist to build efficient and scalable machine learning systems to keep amazon the safest and most trusted place to shop online. In this role, you will drive innovation and lead critical scientific projects. You will work closely with scientists, economists and engineers to build end-to-end ML solutions that have immediate impacts on amazon customers. You will work on a variety of research areas including:· Develop NLP and deep learning models to extract insights from customer feedback.· Build the next generation of risk monitoring system using predictive modeling, graph mining and unsupervised learning techniques.· Apply the state-of-the art Computer Vision technique to develop a highly scalable ML solution for product authentication.· Develop and deploy real-time ML models using AWS services.
US, CA, San Diego
At Amazon, we strive every day to be Earth’s most customer centric company. Amazon Perfect Order Experience (POE) team works to ensure that customers can buy with confidence on Amazon. We develop and implement large scale machine learning solutions to protect the buying experience on Amazon while minimizing friction for our selling partners. We develop state-of-the art Natural Language Processing models to detect negative customer experience in real-time and build an ever-evolving risk monitoring system to proactive protect customer trust.We are looking for an Applied Scientist to build efficient and scalable machine learning systems to keep amazon the safest and most trusted place to shop online. In this role, you will work closely with scientists, economists and engineers to build end-to-end ML solutions that have immediate impacts on amazon customers. You will work on a variety of research areas including:· Develop NLP and deep learning models to extract insights from customer feedback.· Build the next generation of risk monitoring system using predictive modeling, graph mining and unsupervised learning techniques.· Apply the state-of-the art Computer Vision technique to develop a highly scalable ML solution for product authentication.· Develop and deploy real-time ML models using AWS services.
US, CA, San Diego
At Amazon, we strive every day to be Earth’s most customer centric company. Amazon Perfect Order Experience (POE) team works to ensure that customers can buy with confidence on Amazon. We develop and implement large scale machine learning solutions to protect the buying experience on Amazon while minimizing friction for our selling partners. We develop state-of-the art Natural Language Processing models to detect negative customer experience in real-time and build an ever-evolving risk monitoring system to proactive protect customer trust.We are looking for an Applied Scientist to build efficient and scalable machine learning systems to keep amazon the safest and most trusted place to shop online. In this role, you will work closely with scientists, economists and engineers to build end-to-end ML solutions that have immediate impacts on amazon customers. You will work on a variety of research areas including:· Develop NLP and deep learning models to extract insights from customer feedback.· Build the next generation of risk monitoring system using predictive modeling, graph mining and unsupervised learning techniques.· Apply the state-of-the art Computer Vision technique to develop a highly scalable ML solution for product authentication.· Develop and deploy real-time ML models using AWS services.
US, VA, Herndon
Amazon Web Services (AWS) Global Infrastructure is responsible for the management and operational support of Amazons world-wide Data Center locations, and is looking for experienced Data Scientists who have a passion for influencing decision making on a worldwide scale. Our team works with all organizations supporting the Data Center infrastructure and operations. We engage directly with key stakeholders to facilitate data driven decision through advanced analytics and dynamic modelling. The ideal candidate is customer obsessed, innovative, independent, results-oriented and enjoys working in a fast-paced growing organization.An emphasis on pragmatism and applied science is necessary to drive this operationally focused work. An interest in operations, manufacturing or process improvement is helpful. The Central Infrastructure Operations Analytics Team builds metrics and dashboards that monitor the overall health of Data Center Operations. In this dynamic, fast paced and highly ambiguous environment, a focus on iteration and a bias for action are essential. The ability to embrace this ambiguity and work with a highly distributed team of experts is critical. While this is a small team, there is opportunity to own globally impactful work and grow your career in technical, programmatic or people leadership. You will likely work with Python or R, though specific particular modelling language. Your problem solving ability, knowledge of data models and ability to drive results through ambiguity are more important to us.Responsibilities· Engage with internal partner teams to fully understand their operational complexities and challenges.· Translate business problem statements into analysis requirements, and work with internal customers to define best output based on expressed stakeholder needs.· Apply domain knowledge and business judgment to identify opportunities and quantify the impact, aligning research direction to business requirements.· Develop predictive and prescriptive models to enable to remediation of organization challenges.· Manage the design, development and evaluation of highly innovative, scalable models and algorithms.· Deliver solutions to complex problems in support of the business goals.· Define and coordinate the data acquisition requirements for model development and solution implementation.· Design and drive experiments, A/B testing, outlier deep dives and form actionable recommendations, and manage the implementation of those recommendations.· Develop and manage the long-term vision and portfolio of research initiatives.· Coordinate research related activities of cross functional teams for hypothesis testing and validation.· Productionize appropriate models for global implementation and scalability.· Mentor team members for their career development and growth in the areas of Machine Learning and Data Science.·
US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in technology to solve real-world problems. As an Applied Scientist at the intersection of machine learning and the life sciences, you will participate in developing exciting services for customers. Our team rewards 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.The Role:We are looking for an outstanding Machine Learning Scientist that is able to apply Machine Learning theory into practice through experimentation and invention, develop new algorithms using machine learning techniques (such as random forest, Bayesian networks, ensemble learning, clustering) for complex problems, implement prototype for learning systems and work with massive datasets. Amazon has a culture of data-driven decision-making, and the expectation is that analytics are timely, accurate, innovative and actionable.Responsibilities:· Use statistical and machine learning techniques to support the business.· Conduct A/B tests to evaluate new learning algorithms and features.· Establish processes for large-scale data analyses, model development, model validation and model implementation.· Act as a point of contact and machine learning leader for the business.
US, NY, New York
Amazon Advertising is dedicated to driving measurable outcomes for brand advertisers, agencies, authors, and entrepreneurs. Our ad solutions—including sponsored, display, video, and custom ads—leverage Amazon’s innovations and insights to find, attract, and engage intended audiences throughout their daily journeys. With a range of flexible pricing and buying models, including self-service, managed service, and programmatic ad buying, these solutions help businesses build brand awareness, increase product sales, and more.We are seeking an experienced Sr. Data Scientist who will build the experimentation framework and dive deep into complex data sets to identify actionable insights that will maximize the value of our programmatic supply. In this role you will be building an analysis infrastructure to reliably measure offline data and A/B test outcomes using tools and techniques of inferential statistics. You are an analysis expert and a data evangelist who leverages a variety of platforms and analytical tools to extract critical insights from massive data sets.RESPONSIBILITIES:· Analyze large disparate data sets to find actionable insights that lead to business decisions and new opportunities· Proactively and independently work with key stakeholders to translate complex business problems into verifiable hypotheses and use cases using complex, multi-source data· Execute deep-dive analyses addressing key business issues and present findings to stakeholders· Communicate complex analytical insights and business implications with a large range of business and technical stakeholders· Proactively make recommendations for new tests and initiatives to improve key metrics and customer outcomes** Position can be in New York or San Francisco Bay Area
US, NY, New York
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!Are you passionate about Machine Learning, Causal Inference, and Big Data Systems? Does building new state-of-the-art measurement products at petabyte scale get you fired up? Be part of a team of industry leading experts that operates one of the largest analytics and data science ecosystems at Amazon. Amazon is leveraging its highly unique data and applying the latest machine learning and big data technologies available to change the way marketers optimize their advertising spend. Our campaign measurement and reporting systems apply these technologies on terabytes of data a day (over 50B new events per day).You'll be one of the lead scientists tackling some of the hardest problems in advertising; measuring ads incrementality, providing estimated counterfactuals and predicting the success of advertising strategies. You and your team will develop state of the art causal learning, deep learning, and predictive techniques to help marketers understand and optimize their spend.Some things you'll do in this role:· Work closely with other scientists and engineers to analyze our data to develop the best technical design and approach.· Be a hands-on technical leader, developing applications to solve hard problems· Deliver with independence on challenging large scale problems with ambiguity· Write cogent summaries of your work, accessible to other science and business leadersImpact and Career Growth:.· 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 a long-term science vision 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 leadership, organizational ability, technical strength, product focus and business understanding.Why you love this opportunity:· Amazon 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_6Lzw8raEAmazon 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· We are open to hiring in the following cities: Seattle, Chicago, Santa Monica, Arlington, New York City, Austin, Boulder, and Denver.#madsjob#sspajobs
US, WA, Seattle
We’re working on the future. If you are seeking an iterative fast-paced environment where you can drive innovation, apply state-of-the-art technologies to solve extreme-scale real world delivery challenges, and provide visible benefit to end-users, this is your opportunity.Come work on the Prime Air team!We're looking for an outstanding Research Scientist who combines superb technical, research and analytical capabilities with a demonstrated ability to get the right things done quickly and effectively. This person must be comfortable working with a team of top-notch developers and collaborating with our research teams.In this role you will develop, implement and test controls for the Prime Air drone. The ideal candidate will have fundamental knowledge of simulation, dynamics, aerodynamics, design and analysis with some practical real-life implementation experience.Export Control LicenseThis position may require a deemed export control license for compliance with applicable laws and regulations. Placement is contingent on ’s ability to apply for and obtain an export license on your behalf.
US, MA, Metro West
Sr. Applied Scientist - Amazon Physical Stores TechnologiesAmazon is build new technologies to advance physical retails and come join an ambitious project developing new technologies that go well beyond the current state of the art to address an enormous market that will impact the daily lives of tens of millions of people.As a senior applied scientist, you will help solve a variety of technical challenges and mentor other scientists. You will be technical leader in translating business and functional requirements into concrete deliverables and build quick prototypes or proofs of concept in partnership with other technology leaders within the team. You will tackle challenging, novel situations every day and given the size of this initiative, you’ll have the opportunity to work with multiple technical teams at Amazon in different locations. You should be comfortable with a degree of ambiguity that’s higher than most projects and relish the idea of solving problems that, frankly, haven’t been solved before - anywhere. Along the way, we guarantee that you’ll learn a ton, have fun and make a positive impact on millions of people.
US, MA, Metro West
Sr. Applied Scientist - Amazon Physical Stores TechnologiesAmazon is build new technologies to advance physical retails and come join an ambitious project developing new technologies that go well beyond the current state of the art to address an enormous market that will impact the daily lives of tens of millions of people.As a senior applied scientist, you will help solve a variety of technical challenges and mentor other scientists. You will be technical leader in translating business and functional requirements into concrete deliverables and build quick prototypes or proofs of concept in partnership with other technology leaders within the team. You will tackle challenging, novel situations every day and given the size of this initiative, you’ll have the opportunity to work with multiple technical teams at Amazon in different locations. You should be comfortable with a degree of ambiguity that’s higher than most projects and relish the idea of solving problems that, frankly, haven’t been solved before - anywhere. Along the way, we guarantee that you’ll learn a ton, have fun and make a positive impact on millions of people.
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLEEntity: Amazon Web Services, Inc.Title: Economist IILocation: Seattle, WAPosition Responsibilities:Solve key business problems faced in retail, advertising, international retail, cloud computing, third party merchants, search, Kindle, streaming video, and operations through application of economic theory. Apply frontier of economic thinking to market design, pricing, forecasting, program evaluation, and online advertising. Build econometric models using data systems. Develop new techniques to process large data sets, address quantitative problems, and contribute to automated systems design. Apply tools from applied micro-econometrics (e.g. experimental design, difference-in-difference, regression discontinuity, and IV) and forecasting (essential time series models). Leverage big data tools for data extraction. Write up and present analysis for distribution to various levels of management at Amazon.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, WA, Seattle
Why this job is awesome?· · This is SUPER high-visibility work: Our mission is to provide consistent, accurate, and relevant delivery information to every single page on every Amazon-owned site.· · MILLIONS of customers will be impacted by your contributions: The changes we make directly impact the customer experience on every Amazon site. This is a great position for someone who likes to leverage Machine learning technologies to solve the real customer problems, and also wants to see and measure their direct impact on customers.· · We are a cross-functional team that owns the ENTIRE delivery experience for customers: From the business requirements to the technical systems that allow us to directly affect the on-site experience from a central service, business and technical team members are integrated so everyone is involved through the entire development process.· - Do you want to join an innovative team of scientists and engineers who use machine learning and statistical techniques to deliver the best delivery experience on every Amazon-owned site?- Are you excited by the prospect of analyzing and modeling terabytes of data on the cloud and create state-of-art algorithms to solve real world problems?- Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company?- Do you like to innovate and simplify?If yes, then you may be a great fit to join the Delivery Experience Machine Learning team.Major responsibilities:· Lead a ML team to research and implement machine learning and statistical techniques to create scalable and effective models in Delivery Experience (DEX) systems· Solve business problems and to identify business opportunities to provide the best delivery experience on all Amazon-owned sites.· Design, development and evaluation of highly innovative machine learning models for big data.· Analyzing and understanding large amounts of Amazon’s historical business data to detect patterns, to analyze trends and to identify correlations and causalities· Working closely with other software engineering teams to drive real-time model implementations and new feature creations· Establishing scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation
US, MD, Virtual Location - Maryland
Excited by using massive amounts of data to develop Machine Learning (ML) and Deep Learning (DL) models? Want to help public sector, medical center and non-profit agencies derive business value through the adoption of Artificial Intelligence (AI)? Eager to learn from many different enterprise’s use cases of AWS ML and DL? Thrilled to be key part of Amazon, who has been investing in Machine Learning for decades, pioneering and shaping the world’s AI technology?At Amazon Web Services (AWS), we are helping large enterprises build ML and DL models on the AWS Cloud. We are applying predictive technology to large volumes of data and against a wide spectrum of problems. Our Professional Services organization works together with our AWS customers to address their business needs using AI.AWS Professional Services is a unique consulting team. We pride ourselves on being customer obsessed and highly focused on the AI enablement of our customers. If you have experience with AI, including building ML or DL models, we’d like to have you join our team. You will get to work with an innovative company, with great teammates, and have a lot of fun helping our customers.If you do not live in a market where we have an open Data Scientist position, please feel free to apply. Our Data Scientists can live in any location where we have a Professional Service office.A successful candidate will be a person who enjoys diving deep into data, doing analysis, discovering root causes, and designing long-term solutions. It will be a person who likes to have fun, loves to learn, and wants to innovate in the world of AI. Major responsibilities include:· · Understand the customer’s business need and guide them to a solution using our AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances .· · Assist customers by being able to deliver a ML / DL project from beginning to end, including understanding the business need, aggregating data, exploring data, building & validating predictive models, and deploying completed models to deliver business impact to the organization.· · Use Deep Learning frameworks like PyTorch, Tensorflow and MxNet to help our customers build DL models.· · Use SparkML and Amazon Machine Learning (AML) to help our customers build ML models.· · Work with our Professional Services Big Data consultants to analyze, extract, normalize, and label relevant data.· · Work with our Professional Services DevOps consultants to help our customers operationalize models after they are built.· · Assist customers with identifying model drift and retraining models.· · Research and implement novel ML and DL approaches, including using FPGA.· · This position can have periods of up to 10% travel.· · This position requires that the candidate selected be a US Citizen and obtain and maintain an active TS/SCI security clearance.· Here at AWS, 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 we 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.
US, WA, Seattle
Amazon Web Services (AWS) is obsessed with ensuring the success of our customers. To this end, AWS is learning how to best train, compensate, and deploy its large and growing global salesforce. Which payment plans lead to good customer outcomes in the long run? What type of training – and how much – helps drive opportunity creation and win rate? What customers would benefit most from the help of an AWS expert? These are the types of questions our team seeks to answer.AWS is hiring an economist specializing in program evaluation / reduced form causal analysis to help estimate the impact of – and then optimize – different compensation, training, and assignment programs. While causal analysis is our bread and butter, we see opportunities for those who have (or are willing to invest in building) broad skillsets. If you have an EIO or forecasting background, we’d love to talk.Job Locations: Seattle, WA