Adapting Alexa to Regional Language Variations

As Alexa expands into new countries, she usually has to be trained on new languages. But sometimes, she has to be re-trained on languages she’s already learned. British English, American English, and Indian English, for instance, are different enough that for each of them, we trained a new machine learning model from scratch.

Ideally, we wouldn’t have to do that. When Alexa moves into a new country and encounters a language she’s already familiar with, she should be able to take advantage of her previous experience. That’s the idea behind a new machine learning system that my colleagues and I presented last week at the annual meeting of the North American Chapter of the Association for Computational Linguistics.

Our system is a domain classifier, which determines the topic of a customer’s request, such as music, weather, or sports. It can also identify requests as “out of domain”, which is important to prevent the mishandling of unintentional or garbled speech.

The domain classifier is a multi-task model, which means that it’s trained to perform several tasks simultaneously. One of those tasks is to learn a general statistical model for a particular language, which captures consistencies across regions. Its other tasks are to learn several different locale-specific models for the same language. It bases its domain classifications on the outputs of both the general and the locale-specific models.

In experiments in which we trained our model on four different variants of English, it showed accuracy improvements of 18%, 43%, 116%, and 57% versus models trained on each variant individually.

Locale-agnostic_architecture.png._CB462220682_.png
Our new domain classifier includes both a locale-agnostic component (the "shared encoder") and locale-specific components (the k location encoders). The outputs of both are combined as inputs to a bank of locale-specific classifiers (top).

One reason multi-task training for domain classification is challenging is that requests to the same domain could look wildly different in different locales. Requests to the restaurant domain, for instance, would feature much different restaurant names in Mumbai than they would in London, even though customers are requesting the same services — address information, menu information, reservations, and so on.

In such cases, relying on a single locale-specific classifier, trained on data unique to that locale, would probably yield better results than pooling the outputs of several locale-specific classifiers. In other cases, however, where requests are more uniform across locales, the outputs of several different locale-specific models could reinforce each other, improving accuracy.

To strike a balance between these two types of cases, we use an attention mechanism, which gives different emphases — or weights — to the outputs of different locale-specific models, depending on the input. Ideally, in cases like the restaurant example, in which input data is very locale-dependent, the attention mechanism would assign almost of all of its weight to a single locale-specific model, ignoring the outputs of the other locale-specific models.

In advance, we can identify domains that should receive this kind of treatment, because their input data is highly locale dependent. But at run time, our system doesn’t know which domain a request is intended for. Answering that question is precisely what it’s trying to do.

We resolve this conundrum by modifying the training mechanism. At training time, we do know which domain each input is intended for, because the training data is labeled. During training, we evaluate the system not only on how accurately it classifies domains but also on how consistently the attention mechanism prioritizes the right locale-specific model when it receives locale-dependent data.

The outputs of the locale-specific models are combined into a single vector, with heavily weighted outputs contributing more to the vector’s final values than lower-weighted outputs. That vector is concatenated with the output of the locale-independent model, and the combined vector passes to another network layer for domain classification.

We evaluated this architecture using English-language data from the U.S., the U.K., India, and Canada. We trained our multi-task model on all four data sets and compared its performance to that of locale-specific models trained separately on the same data sets. That’s the experiment that yielded the accuracy improvements reported above.

We also conducted one more experiment, in which we used adversarial training to enforce the neutrality of the locale-independent model. That is, during training, in addition to evaluating the system’s performance on domain classification accuracy and routing of locale-dependent data, we also evaluated it on how badly the locale-independent model predicted locales.

This was an attempt to force the locale-independent model to extract only those characteristics of the data that were consistent across locales. In general, however, this hurt the system’s overall performance. The one exception was on the U.K. data set, where adversarial training conferred a slight performance boost. In ongoing work, we’re trying to determine the reason for that improvement.

Acknowledgments: Jihwan Lee, Ruhi Sarikaya

About the Author
Young-Bum Kim is an Amazon science leader in the Alexa AI organization.

Related content

Amazon Science Newsletter Project Kuiper.jpg
Get more from Amazon Science
Sign up for our monthly newsletter

Work with us

See More Jobs
US, CA, Cupertino
Are you passionate about applying formal verification, program analysis, constraint-solving, and theorem proving to real world problems? Do you want to create products that help customers? If so, then we have an exciting opportunity for you. In this role, you will interact with internal teams and external customers to understand their requirements. You will apply your knowledge to propose innovative solutions, create software prototypes, and productize prototypes into production systems using software development tools and methodologies. In addition, you will support and scale your solutions to meet the ever growing demand of customer use.Technical Responsibilities:- Interact with various teams to develop an understanding of their security and safety requirements.- Apply the acquired knowledge to build tools find problems, or show the absence of security/safety problems.- Implement these tools through the use of SAT, SMT, BDDs, and various concepts from programming languages, theorem proving, formal verification and constraint solving.- Perform analysis of the customer systems using tools developed in-house or externally provided- Create software prototypes to verify and validate the devised solutions methodologies; integrate the prototypes into production systems using standard software development tools and methodologies.Leadership Responsibilities:- Can present and defend company-wide technical decisions to the internal technical community and represent the company effectively at technical conferences.- Functional thought leader, sought after for key tech decisions. Can successfully sell ideas to an executive level decision maker.- Mentors and trains the research scientist community on complex technical issues.AWS has the most services and more features within those services, than any other cloud provider–from infrastructure technologies like compute, storage, and databases–to emerging technologies, such as machine learning and artificial intelligence, data lakes and analytics, and Internet of Things. Whether its Identity features such as access management and sign on, cryptography, console, builder & developer tools, and even projects like automating all of our contractual billing systems, AWS Platform is always innovating with the customer in mind. The AWS Platform team sustains over 750 million transactions per second.We have a formal mentor search application that lets you find a mentor that works best for you based on location, job family, job level etc. Your manager can also help you find a mentor or two, because two is better than one. In addition to formal mentors, we work and train together so that we are always learning from one another, and we celebrate and support the career progression of our team members.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.Our team also 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, which is why we aren’t focused on how many hours you spend at work or online. Instead, we’re happy to offer a flexible schedule so you can have a more productive and well-balanced life—both in and outside of work.
US, NY, New York
AWS has the most services and more features within those services, than any other cloud provider–from infrastructure technologies like compute, storage, and databases–to emerging technologies, such as machine learning and artificial intelligence, data lakes and analytics, and Internet of Things. AWS Platform is the glue that holds the AWS ecosystem together. Whether its Identity features such as access management and sign on, cryptography, console, builder & developer tools, and even projects like automating all of our contractual billing systems, AWS Platform is always innovating with the customer in mind. The AWS Platform team sustains over 750 million transactions per second.About the Team. Would you like to join the team that protects the global AWS platform from fraud? Do you enjoy thinking like a fraudster and using your technical skills to help detect & mitigate AWS accounts from being compromised? If so, AWS Fraud Prevention has an exciting opportunity for you.The AWS Fraud Prevention Compromise vertical is responsible for detecting & mitigating AWS account compromise. You’ll be part of a team of Data Scientists, Investigations Analysts, and Technical & non-Technical Program Managers. The team’s goal is to identify and neutralize fraudsters from compromising AWS customers’ accounts.About the Role. As a Data Scientist, you will work directly with Business Analysts and Software Development Engineers to monitor the flavor/ trend of compromise on AWS worldwide and design appropriate solutions to respond in a collaborative environment. There are no walls, and success is determined by your ability to dive deep, and understand the subtle demands new and complex services will place upon systems and teams. As a Data Scientist your responsibilities will include:· Protecting AWS customers and the AWS business from compromise actors.· Manage your own process: identify and execute on high impact projects, triage external requests, and make sure you bring projects to conclusion in time for the results to be useful.· Apply state-of-the-art Machine Learning methods to large amounts of data from different sources to build and productionalize fraud prevention, detection and mitigation solutions.· Keep up with and contribute to the progress of the Amazon and broader ML research communities in the context of fraud prevention.· Deep dive on the problems using SQL and scripting languages like Python/R to drive short term and long term solutions leveraging Statistical Analysis.· Analyze data (past customer behavior, sales inputs, and other sources) to figure out trends, create compromise prevention and mitigation solutions and output reports with clear recommendations.· Collaborate closely with the development team to recommend and build innovations based on Data Science.· Handle escalations from AWS Management for fraud, compromise and related activities.· Be the primary point of contact during compromise outbreaks – including analyses to identify and apply responses.· Collaborate in a fast paced environment with multiple teams and customers in a dynamic entrepreneurial organization.Learn and Be Curious. We have a formal mentor search application that lets you find a mentor that works best for you based on location, job family, job level etc. Your manager can also help you find a mentor or two, because two is better than one. In addition to formal mentors, we work and train together so that we are always learning from one another, and we celebrate and support the career progression of our team members.Inclusion and Diversity. Our team is diverse! We drive towards an inclusive culture and work environment. We are intentional about attracting, developing, and retaining amazing talent from diverse backgrounds. Team members are active in Amazon’s 10+ affinity groups, sometimes known as employee resource groups, which bring employees together across businesses and locations around the world. These range from groups such as the Black Employee Network, Latinos at Amazon, Indigenous at Amazon, Families at Amazon, Amazon Women and Engineering, LGBTQ+, Warriors at Amazon (Military), Amazon People With Disabilities, and more.Learn more about Amazon on our Day 1 Blog: https://blog.aboutamazon.comAmazon 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.
US, WA, Seattle
Amazon’s mission is to be the most customer-centric company in the world. In support of this mission, the Employee Services organization strives to create a frustration-free environment allowing all Amazonians to focus on delivering, innovating and inventing for our customers. With all Amazonians has our customer, the Employee Experience Insights & Analytics team is seeking an applied behavioral/research scientist toexecute controlled, scientific research experiments to test hypotheses and provide stakeholders with otherwise unknown answers to important, high-priority HR questions.This team member will be responsible for designing and implementing metrics to better understand and solve the challenges within the employee experience while tracking impact to different business/operation area(s) bottom-line. We seek expertise in survey methodology, experimental design, sampling, data collection, extraction, psychometrics and analytics for success in this role. Relentless customer-orientation, constant curiosity, translation of research insight into business outcomes, openness to collaboration and personal development, and a commitment to the highest standards of methodological rigor and experimental design are a must.This role provides opportunity for significant exposure to Amazon’s culture, HR leadership, and global businesses; in addition to the opportunity to expand the team.Key Responsibilities· Lead the Data Science and Experimentation program· People manager experience leading data scientists, business analysts and/or business intelligence engineers· Provide expertise in applied behavioral research.· Define the appropriate combination of direct employee feedback and operational metrics and develop metrics to measure the health of employee experience for various services.· Conduct quantitative research to solve methodological problems.· Manage large-scale research projects.· Solve complex problems by selecting the ideal solution from a wide range of data science methodologies.· Develops end-to-end solutions.· Advances modelling and inference techniques.· Influences multiple teams.· Able to build consensus.· Advises Sr. Manager/Director/VP leaders.· Actively mentors/develops others.
US, WA, Seattle
Amazon Advertising seeks an Economist to help develop an automated financial forecasting system for our DSP advertising business, and help model key relationships that drive advertiser value and impact our financial performance. We are looking for a motivated candidate who has operated successfully in a fast-paced, global, results-oriented environment and has the ability to influence the decisions of senior business leaders through effective verbal and written communication, logical reasoning, and the presentation of analyses. The successful candidate will collaborate closely with business teams to help execute and shape our product and financial strategy.If you enjoy using Econometric methods to shape strategy and build new initiatives from concept to full-scale operations this will be a good match. We are looking for a highly motivated individual to develop deep industry understanding, create new models gaining insight into advertising performance, analyze monetization strategies to maximize revenue, and provide guidance for feature roadmap prioritization and decision-making. This position will collaborate with business leaders on a daily basis and will be contributing to overall financial modeling and analysis during our operating cycle plans, periodic forecast updates, requirements planning, business reviews, and providing business insights into key initiatives.The successful candidate will be a self-starter who is comfortable with ambiguity; dives deep into data to find key relationships, creates models to better understand and forecast processes, is detail oriented and has the ability to work well with cross-functional teams including product development, science, sales, other finance teams, and senior leaders.
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, WA, Seattle
Are you seeking an environment where you can drive innovation? Do you want to apply machine learning techniques and advanced statistical modeling to solve real world problems to help Amazon reach and delight millions of customers around the world? Do you want to play a crucial role in the future of Amazon?Every time an Amazon customer makes an order they leverage the most advanced and sophisticated supply chain the world has ever seen, Amazon Operations, and its global network comprising of cutting edge software, fulfillment centers, sort centers, delivery stations, airports, customer service centers, physical stores, robots, airplanes, trucks, vans, trucks, world class employees, trusted partners, and more. Conducting a symphony of this scale comes with significant costs. It also comes with the largest repository of supply chain data to exist that’s growing by billions of data points by the minute.Here in Consumer Controllership Data Science our data scientists raise the bar on our ability to fulfill promises to customers at greater convenience, speed, and value through:· Leveraging the largest repository of supply chain data to ever exist to develop models to forecast, classify, and detect anomalous costs.· Working with technical and non-technical customers across every step of data science project life cycle.· Collaborating with our dedicated product, data engineering, and software development teams to create production implementations for large-scale data analysis.· Developing an understanding of key business metrics / KPIs and providing clear, compelling analysis that shapes the direction of our business.· Presenting research results to our internal research community.· Leading training and informational sessions on our science and capabilities.Your contributions will be seen and recognized broadly within Amazon, potentially contributing to the Amazon research corpus and patent portfolio.Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation / Age
US, NC, Virtual Location - N Carolina
The AWS Central Economics team is looking for a PhD economist. The ideal candidate will have experience with time-series forecasting.You will learn about cloud products, including compute, storage, and databases. You will work on analytic projects requested by senior leadership. You will get the opportunity to learn new techniques. You will be a part of a team with many experienced economists.
US, WA, Seattle
Compensation Science is building economic models and algorithms from the ground up to design and scale pay for hundreds of thousands of Amazon employees worldwide. The fast-growing, interdisciplinary team is working at the intersection of economics, machine learning, and product development.We are looking for an outstanding, end-to-end economist who is able to provide structure to ambiguous, complex business problems, conduct causal econometric analysis, work with engineers to launch science models in product, and measure the impact of policy changes.This role will build and operationalize econometric models for new compensation products owned by the team and initiate high impact projects in the compensation and benefits space. Economists at Amazon have access to engineering and econometric tools and opportunities to learn new econometric and machine learning methods from world-class scholars.Responsibilities:· Own the development of economic models and econometric analysis· Assist in the delivery of automated, scalable analytic models· Work collaboratively with economists, scientists, and engineers on the team and across the HR organization· Interpret and communicate results to global business stakeholders
CA, BC, Vancouver
The Economic Technology team (EconTech) is looking for a Research Scientist to build Reinforcement Learning solutions to solve economic problems at scale. EconTech uses Machine Learning, Reinforcement Learning, Causal Inference, and Econometrics/Economics to derive actionable insights about the complex economy of Amazon’s retail business. We also develop statistical models and algorithms to drive strategic business decisions and improve operations. We are an interdisciplinary team of Economists, Engineers, and Scientists incubating and building disruptive solutions using cutting-edge technology to solve some of the toughest business problems at Amazon.You will work with business leaders, scientists, and economists to translate business and functional requirements into concrete deliverables, including the design, development, testing, and deployment of highly scalable distributed services. You will partner with scientists, economists, and engineers to help invent and implement scalable ML, RL, and econometric models while building tools to help our customers gain and apply insights. This is a unique, high visibility opportunity for someone who wants to have business impact, dive deep into large-scale economic problems, enable measurable actions on the Consumer economy, and work closely with scientists and economists. We are particularly interested in candidates with experience building predictive models and working with distributed systems.As a Research 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.
US, CA, San Diego
The Economic Technology team (EconTech, ET) is looking for an a experienced Applied Scientist Manager to build Reinforcement Learning solutions to solve economic problems at scale. ET uses Machine Learning, Reinforcement Learning, Causal Inference, and Econometrics/Economics to derive actionable insights about the complex economy of Amazon’s retail business. We also develop Statistical Models and Algorithms to drive strategic business decisions and improve operations. We are an interdisciplinary team of Economists, Engineers, and Scientists incubating and building disruptive solutions using cutting-edge technology to solve some of the toughest business problems at Amazon.You will lead multiple teams of engineers, scientists, and economists to translate business and functional requirements into concrete deliverables, including the design, development, testing, and deployment of highly scalable distributed services. You will provide thought leadership to scientists, economists, and engineers to help invent and implement scalable ML, RL, and econometric models while building tools to help our customers gain and apply insights. This is a unique, high visibility opportunity for a leader who wants to have business impact, dive deep into large-scale economic problems, and enable measurable actions on the Consumer economy. We are particularly interested in candidates with experience building predictive models and working with distributed systems.As a Manager, Applied Science, 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..As an Applied Science Manager, you will:· Lead a group of talented applied scientists and software engineers to deliver machine-learning and AI solutions to production.· Advance team's engineering craftsmanship and drive continued scientific innovation as a thought leader and practitioner.· Develop science and engineering roadmap, run Sprint/quarter and annual planning, and foster cross-team collaboration to execute complex projects.· Perform hands-on data analysis, build machine-learning models, run regular A/B tests, and communicate the impact to senior management.· Hire and develop top talents, provide technical and career development guidance to both scientists and engineers in the organization.
US, CA, Virtual Location - California
Are you passionate about conducting research to improve people’s lives? Would you like to impact more than one million Amazonians globally and improve their employee experience? If so, you should consider joining Organizational Research and Measurement (ORM) for World Wide Consumer Talent. Our goal is to be the best and most diverse workforce in the world. ORM uses science, research and technology to optimize employee experience and performance across the full employee lifecycle, from first contact through exit.We are looking for economists to join a new team that focuses on the economic issues of more than one million associates at Amazon. The economist will work with data scientists and data engineers to frame ambiguous and complex business problems into specific scientific questions, design experiments and develop models using large scale data, and transform the insights into improved policies and products at scale. Ideal candidates should have business acumen, technical skills in causal inference, and be able to communicate the insights to multiple audiences (e.g., scientific peers, functional teams and business leaders).
US, VA, Herndon
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 customers 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 (D.C, Maryland, Virginia, Illinois, Pennsylvania, New York, New Jersey) where we have a WWPS Professional Service office.We’re looking for top architects, system and software engineers capable of using ML and other techniques to design, evangelize, and implement state-of-the-art solutions for never-before-solved problems.The primary responsibilities of this role are to:· Design data architectures and data lakes· Provide expertise in the development of ETL solutions on AWS· Use ML tools, such as Amazon SageMaker Ground Truth (GT) to annotate data. Work with Professional Services on designing workflow and user interface for GT annotation.· Collaborate with our data scientists to create scalable ML solutions for business problems· Interact with customer directly to understand the business problem, help and aid them in implementation of their ML ecosystem· Analyze and extract relevant information from large amounts of historical data — provide hands-on data wrangling expertise· Work closely with account team, research scientist teams and product engineering teams to drive model implementations and new algorithms· This position can have periods of up to 10% travel.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.Our team also 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, which is why we aren’t focused on how many hours you spend at work or online. Instead, we’re happy to offer a flexible schedule so you can have a more productive and well-balanced life—both in and outside of work.
US, WA, Bellevue
In this role you will help lead a large-scale modeling initiative that spans five global organizations and over twenty teams. You will model weather’s impact on business metrics and focus on the integration of how weather impacts Amazon’s network.Your day-to-day will include model and algorithm development, experiment design, and deep dive analysis. You will learn current processes, build data backed solutions, educate diverse stakeholder groups, and audit implementation. You will work closely with our tech team to launch your solutions into production and build the metrics needed to monitor and improve their performance.Amazon’s extensive logistics system is comprised of thousands of fixed infrastructure nodes, with millions of possible connections between them, and dozens of different transportation methods. Billions of packages flow through this network on a yearly basis, making the impact of optimal improvements unparalleled. This magnificent challenge is an opportunity to drive lasting impact in the design of one of the world’s most complex logistic systems and improve the experience of millions of customers every day. Come build with us!A successful candidate in this position will be able to; communicate across diverse stakeholders, prioritize competing requests, and quantify decisions made. The ideal candidate will demonstrate deep understanding of statistical and machine learning concepts, a strong background in atmospheric science, and a high standard for coding best practices.Amazon offers competitive packages including comprehensive health care, 401(k), restricted stock units, growth potential and a challenging and exciting work environment.Amazon is an Equal Opportunity Employer – Minority / Women / Disability / Veteran / Gender Identity / Sexual Orientation / Age.
US, WA, Seattle
Are you passionate about building an experimental culture while creating and delivering differentiated values for our customers? This is a rewarding role where you will be able to draw a clear connection between your work and how it improves customer trust and experience of millions of Amazon customers globally. Help us reinvent risk management to create a resounding impact for our customers.We are looking for an Applied Scientist to join the Risk Analytics & Insights team and shape our team’s vision, build risk products and execute delivering our big ideas in risk management. In this role, you should be comfortable working independently with the ability to prioritize workloads, remain flexible, and maintain a strong attention to detail in a fast-paced environment. You will evaluate existing and new technologies required for a solution. You will work with a cross-function team (science, product, engineers, risk manager) to apply your specialized expertise to invent, design, and build innovative software that are stable and performant. You will deliver artifacts with the proper level of complexity the first time (or at least minimize incidental complexity). You will make appropriate trade-offs, re-use where possible, and are judicious about introducing dependencies. You are efficient with resource usage (e.g., hardware, data storage, etc.). You will also be involved in the broader scientific community (e.g., give invited talks, lectures, review for conferences).Key role responsibilities include:· Research, design and implement scalable machine learning (ML), natural language, or computational models to solve problems that matter to our customers in an iterative fashion.· Lead the design, implementation, and successful delivery of large, critical, or difficult scientific solutions involving a significant amount of work while delivering solutions with complete independence.· Map business requirements and customer needs to a scientific problem while providing structure around complex risk decision-making problems.· Align the research direction to business requirements and make the right judgments on research and development schedule and prioritization· Contribute to operational excellence in your team’s scientific components, constructively identifying problems and proposing solutions, taking on projects that improve those components, making them better and easier to maintain.· Mentor and develop junior applied scientists/interns or developers who work on data science and ML/AI problems in the same organization.· Stay informed on the latest machine learning, natural language and/or artificial intelligence trends and make presentations to the larger engineering and applied science communities.
US, WA, Seattle
Are you customer-obsessed, data oriented, and confident in proposing opportunities to improve our customers’ experience across different Amazon businesses? Amazon is looking for an experienced, talented and highly motivated individual to join our Customer Experience Strategy team! We are seeking a Research Scientist with a passion for NLP and Machine Learning model creation. You will be part of the team that adds new capabilities with multiple visual / audio analytic methodologies. The solutions heavily leverage AI and quantitative analysis to challenge conventional wisdom with hard data.As technology is advancing in unprecedented pace, Amazon Customer Experience Strategy is also evolving with cutting-edge engineering solutions. Our mission is to build end to end products and measure the customer experience of Amazon digital products around the world. We are a group of people who are inspired by inventions every day. We are obsessed with better customer experience for Prime Video, Alexa, Twitch… and the list goes on.Wait, how do we automate all the customer experience measurement? How do we know our products are faster / smoother / smarter? Well, here is a shortlist of technologies we’ve immersed ourselves into regularly.· Speech recognition and natural language (NLP) understanding· Computer Vision, including both Open CV and our own deep learning models.· Robotics and automation· Your role is to study the cutting-edge problems in NLP in order to provide the best-possible experience for our customers. As a Research Scientist, you will develop novel algorithms and modeling techniques to advance the state of the art, and simplify the path to apply these advances to measure the quality of Amazon’s latest devices and services product. You will build relationships with stakeholders and partner teams across multiple orgs, analyze data for trends, select suitable rule-based or machine-learning based techniques and advise team members, closing the loop through data, model, application and customer feedback. You will also leverage Amazon’s heterogeneous data sources and large-scale computing resources.You will work in a small science team with a fast-pace, self-driven environment. You will lead building the NLP algorithms and work with scientists who have deep domain knowledge in Computer Vision, Audio Processing, Signal Processing and Data Science. You team with a group of hardware and software engineers to build intelligent Robotics as well as large, scalable cloud services. You will get strong support from the engineering team during the stages of data capturing, model evaluation and model deployment, so that you can dedicate your time in algorithm research.
US, VA, Virtual Location - Virginia
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
Our vision at Amazon Comprehend Medical is to simplify and advance Natural Language Processing (NLP) in Healthcare. We are building a team of passionate people who are focused on changing the world for the better. Our mission is to provide a delightful experience to Amazon’s customers by pushing the envelope in Automatic Speech Recognition (ASR), Machine Translation (MT), Natural Language Understanding (NLU), Imaging and Machine Learning (ML). If you want your work to positively impact the lives of millions of people and you’re up for a challenge, let’s talk!We are looking for a passionate, talented, and inventive Senior Applied Scientists who can bring bleeding edge machine learning and NLP techniques into real products solving real problems together with a highly multi-disciplinary team of scientist, engineers, strategic partners, product managers and subject domain experts.
US, FL, Virtual Location - Florida
The AWS Central Economics team is looking for a PhD economist. The ideal candidate will have experience with time-series forecasting.You will learn about cloud products, including compute, storage, and databases. You will work on analytic projects requested by senior leadership. You will get the opportunity to learn new techniques. You will be a part of a team with many experienced economists.
US, WA, Bellevue
Are you interested in applying your strong quantitative analysis and big data skills to world-changing problems? Are you interested in driving the development of methods, models and systems for state-of-the-art robotics, transportation and fulfillment systems? If so, then this is the job for you.The Amazon Transportation Services team is responsible for developing an in-depth understanding of our current network and designing our future networks. We are looking for a motivated and experienced Data Science Lead with outstanding leadership skills, proven ability to develop, automate, and manage analytical models of our systems. The successful candidate will have strong modeling skills and is comfortable owning their own data and working from concept through to execution. This role will also build tools and support structures needed to analyze data, dive deep into data to determine root cause of forecast/buying systems errors & changes, and present findings to business partners to drive improvements.A qualified candidate must have demonstrated ability to manage large-scale modeling projects, identify requirements and build methodology and tools that are statistically grounded. The ideal candidate will have experience collaborating across organizational boundaries, applying statistical methods to data, developing optimization and machine learning models.Want to learn more about working with Amazon Transportation Services? Check out this video! https://www.youtube.com/watch?v=en5YqrtBGvY&feature=youtu.be#NALH
US, CA, San Diego
The Economic Technology team (ET) is looking for a Senior Applied Scientist to join our team in building Reinforcement Learning solutions at scale. The ET applies Machine Learning, Reinforcement Learning, Causal Inference, and Econometrics/Economics to derive actionable insights about the complex economy of Amazon’s retail business. We also develop Statistical Models and Algorithms to drive strategic business decisions and improve operations. We are an interdisciplinary team of Economists, Engineers, and Scientists incubating and building day one solutions using cutting-edge technology, to solve some of the toughest business problems at Amazon.You will work with business leaders, scientists, and economists to translate business and functional requirements into concrete deliverables, including the design, development, testing, and deployment of highly scalable distributed services. You will partner with scientists, economists, and engineers to help invent and implement scalable ML, RL, and econometric models while building tools to help our customers gain and apply insights. This is a unique, high visibility opportunity for someone who wants to have business impact, dive deep into large-scale economic problems, enable measurable actions on the Consumer economy, and work closely with scientists and economists. We are particularly interested in candidates with experience building predictive models and working with distributed systems.As a Senior Applied Scientist, you bring business and industry context to science and technology decisions. 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, acquiring expertise as needed. You decompose complex problems into straightforward solutions.