Two new papers discuss how Alexa recognizes sounds

Last year, Amazon announced the beta release of Alexa Guard, a new service that lets customers who are leaving the house instruct their Echo devices to listen for glass breaking or smoke and carbon dioxide alarms going off.

At this year’s International Conference on Acoustics, Speech, and Signal Processing, our team is presenting several papers on sound detection. I wrote about one of them a few weeks ago, a new method for doing machine learning with unbalanced data sets.

Today I’ll briefly discuss two others, both of which, like the first, describe machine learning systems. One paper addresses the problem of media detection, or recognizing when the speech captured by a digital-assistant device comes from a TV or radio rather than a human speaker. In particular, we develop a way to better characterize media audio by examining longer-duration audio streams versus merely classifying short audio snippets. Media detection helps filter a particularly deceptive type of background noise out of speech signals.

For our other paper, we used semi-supervised learning to train a system developed from an external dataset to do acoustic-event detection. Semi-supervised learning uses small sets of annotated training data to leverage larger sets of unannotated data. In particular, we use tri-training, in which three different models are trained to perform the same task, but on slightly different data sets. Pooling their outputs corrects a common problem in semi-supervised training, in which a model’s errors end up being amplified.

Our media detection system is based on the observation that the audio characteristics we would most like to identify are those common to all instances of media sound, regardless of content. Our network design is an attempt to abstract away from the properties of particular training examples.

Like many machine learning models in the field of spoken-language understanding, ours uses recurrent neural networks (RNNs). An RNN processes sequenced inputs in order, and each output factors in the inputs and outputs that preceded it.

We use a convolutional neural network (CNN) as feature extractor, and stack RNN layers on top of it. But each RNN layer has only a fraction as many nodes as the one beneath it. That is, only every third or fourth output from the first RNN provides an input to the second, and only every third or fourth output of the second RNN provides an input to the third.

Pyramidal.jpg._CB465895532_.jpg
A standard stack of recurrent neural networks (left) and the “pyramidal” stack we use instead

Because the networks are recurrent, each output we pass contains information about the outputs we skip. But this “pyramidal” stacking encourages the model to ignore short-term variations in the input signal.

For every five-second snippet of audio processed by our system, the pyramidal RNNs produce a single output vector, representing the probabilities that the snippet belongs to any of several different sound categories.

But our system includes still another RNN, which tracks relationships between five-second snippets. We experimented with two different ways of integrating that higher-level RNN with the pyramidal RNNs. In the first, the output vector from the pyramidal RNN simply passes to the higher-level RNN, which makes the final determination about whether media sound is present.

In the other, however, the higher-level RNN lies between the middle and top layers of the pyramidal RNN. It receives its input from the middle layer, and its output, along with that of the middle layer, passes to the top layer of the pyramidal RNN.

contextual_2.jpg._CB465896350_.jpg
In the second of our two contextual models, a high-level RNN (red circles) receives inputs from one layer of a pyramidal RNN (groups of five blue circles), and its output passes to the next layer (groups of two blue circles).

This was our best-performing model. When compared to a model that used the pyramidal RNNs but no higher-level RNN, it offered a 24% reduction in equal error rate, which is the error rate that results when the system parameters are set so that the false-positive rate equals the false-negative rate.

Our other ICASSP paper presents our semi-supervised approach to acoustic-event detection (AED). One popular and simple semi-supervised learning technique is self-training, in which a machine learning model is trained on a small amount of labeled data and then itself labels a much larger set of unlabeled data. The machine-labeled data is then sorted according to confidence score — the system’s confidence that its labels are correct — and data falling in the right confidence window is used to fine-tune the model.

The model, that is, is retrained on data that it has labeled itself. Remarkably, this approach tends to improve the model’s performance.

But it also poses a risk. If the model makes a systematic error, and if it makes it with high confidence, then that error will feed back into the model during self-training, growing in magnitude.

Tri-training is intended to mitigate this kind of self-reinforcement. In our experiments, we created three different training sets, each the size of the original — 39,000 examples — by randomly sampling data from the original. There was substantial overlap between the sets, but in each, some data items were oversampled, and some were undersampled.

We trained neural networks on all three data sets and saved copies of them, which we might call initial models. Then we used each of those networks to label another 5.4 million examples. For each of the initial models, we used machine-labeled data to re-train it only if both of the other models agreed on the labels with high confidence. In all, we retained only 5,000 examples out of the more than five million in the unlabeled data set.

Finally, we used six different models to classify the examples in our test set: the three initial models and the three retrained models. On samples of three sounds — dog sounds, baby cries, and gunshots — pooling the results of all six models led to reductions in equal-error rate (EER) of 16%, 26%, and 19%, respectively, over a standard self-trained model.

Of course, using six different models to process the same input is impractical, so we also trained a seventh neural network to mimic the aggregate results of the first six. On the test set, that network was not quite as accurate as the six-network ensemble, but it was still a marked improvement over the standard self-trained model, reducing EER on the same three sample sets by 11%, 18%, and 6%, respectively.

Acknowledgments: Qingming Tang, Chieh-Chi Kao, Viktor Rozgic, Bowen Shi, Spyros Matsoukas, Chao Wang

About the Author
Senior Speech Scientist in the Alexa Speech Group at Amazon.

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, CA, San Diego
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 hackers and bad actors? Do you want to build advanced algorithmic systems that help manage the trust and safety of millions of customer every day? Are you excited by the prospect of analyzing and modeling terabytes of data and create state-of-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 the Amazon Account Integrity team.The Amazon Account Integrity team works to ensure that customers are protected from bad actors trying to access their accounts. Our greatest challenge is protecting customer trust without unjustly harming good customers. To strike the right balance, we invest in mechanisms which allow us to accurately identify and mitigate risk, and to quickly correct and learn from our mistakes. This strategy includes continuously evolving enforcement policies, iterating our Machine Learning risk models, and exercising high‐judgement decision‐making where we cannot apply automation.Main responsibilities· Use statistical and machine learning techniques to create scalable risk management systems· Analyzing and understanding large amounts of Amazon’s historical business data for specific instances of risk or broader risk trends· Design, development and evaluation of highly innovative models for risk management· Working closely with software engineering teams to drive real-time model implementations and new feature creations· Working closely with operations staff to optimize risk management operations· Establishing scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation· Tracking general business activity and providing clear, compelling management reporting on a regular basis· Research and implement novel machine learning and statistical approaches
US, MA, North Reading
The Research and Advanced Development team at Amazon Robotics is seeking passionate, hands-on scientists to work on cutting edge algorithms to power automation in Amazon’s order fulfillment and transportation network. Our multi-disciplinary team includes scientists with backgrounds in AI planning and scheduling, robotic grasping and manipulation, machine learning, and operations research. We work on problems such as:- Dynamic allocation and scheduling of tasks to thousands of robots- Learning how to manipulate all the products that Amazon sells- Planning and coordinating the paths of thousands of robots- Co-design of robotic logistics processes and the algorithms to optimize themThe ideal candidate for this position will be familiar with planning or learning algorithms at both the theoretical and implementation levels. You will have the chance to solve complex scientific problems and see your solutions come to life in Amazon’s warehouses!
US, WA, Virtual Location - Washington
The intern will be placed in a large economic team with 10+ full time economists and 3 other interns in the cohort.A day in the lifeTalk with business people to understand business context.Brainstorm with peer economists.Network with other economists and scientists on the team.About the hiring groupThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.Job responsibilitiesThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement.Roughly 50% of research assistants from previous cohorts have converted to full-time employment at Amazon.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, WA, Virtual Location - Washington
The intern will be placed in a large economic team with 10+ full time economists and 3 other interns in the cohort.A day in the lifeTalk with business people to understand business context.Brainstorm with peer economists.Network with other economists and scientists on the team.About the hiring groupThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.Job responsibilitiesThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement.Roughly 50% of research assistants from previous cohorts have converted to full time employment at Amazon.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, WA, Virtual Location - Washington
The intern will be placed in a large economic team with 10+ full time economists and 3 other interns in the cohort.A day in the lifeTalk with business people to understand business context.Brainstorm with peer economists.Network with other economists and scientists on the team.About the hiring groupThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.Job responsibilitiesThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement.Roughly 50% of research assistants from previous cohorts have converted to full time data science or economics employment at Amazon.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, CA, San Francisco
About Us:Launched in 2011, Twitch is a global community that comes together each day to create multiplayer entertainment: unique, live, unpredictable experiences created by the interactions of millions. We bring the joy of co-op to everything, from casual gaming to outstanding esports to anime marathons, music, and art streams. Twitch also hosts TwitchCon, where we bring everyone together to celebrate and grow their personal interests and passions. We're always live at Twitch. Keep an eye on all things Twitch on LinkedIn, Twitter and on our Blog.About the Role:Twitch Commerce helps communities grow by allowing viewers to show their monetary support to creators through patronage. We take pride in our mission to help creators build communities and earn a living entertaining them. The scale and diversity of users, transactions, social interactions and communities presents an exciting opportunity to use our data to personalize experiences for our users.The Commerce ML team is chartered to build and operate the ML models underpinning Twitch Commerce. For example, we work with our product teams to create production models that protect our business and users from fraud and invigorate the financial vitality of our communities by making every gift subscription matter.As a Senior Applied Scientist on the Commerce ML team, you will build solutions and experiments at scale. Twitch data is unique-- granular structured event data, graphs of user interactions, raw live video, and chat. Using it to make a difference for our customers is a rewarding technical challenge for the right contributor leading to immediate monetary impact for creators and for Twitch. This is a green-field territory that combines science leadership, technical strength, and product empathy. Come join us!You Will:· Contribute to and own a piece of the long-term machine learning vision for Commerce, motivated by the needs of our customers, translating that direction into specific plans for applied scientists, s engineering, product, and design teams.· Design, prototype and implement Machine Learning (ML) algorithms· Develop the production data pipelines and ML pipelines on which those algorithms operate· Work with investigators, analysts, PMs and SDEs to turn ever-evolving insights about our users into automated services.· Mentor junior scientists and engineers
CA, ON, Toronto
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!As a Data Scientist on this team you will:· Solve real world problems by analyzing large amounts of business data, diving deep to identify business insights and opportunities, designing simulations and experiments, developing statistical and ML models by tailoring to business needs, and collaborating with Scientists, Engineers, BIE's, and Product Managers.· Translate business questions and concerns into specific quantitative questions that can be answered with available data using sound methodologies. In cases where questions cannot be answered with available data, work with engineers to produce the required data.· Deliver with independence on challenging large scale problems with ambiguity.· Manage and drive the technical and analytical aspects of Advertiser segmentation; continually advance approach and methods.· Retrieve, synthesize, and present critical data in a format that is immediately useful to answering specific questions or improving system performance.· Analyze historical data to identify trends and support decision making.· Improve upon existing methodologies by developing new data sources, testing model enhancements, and fine-tuning model parameters.· Provide requirements to develop analytic capabilities, platforms, and pipelines.· Apply statistical or machine learning knowledge to specific business problems and data.· Formalize assumptions about how our systems are expected to work, create statistical definition of the outlier, and develop methods to systematically identify these outliers. Work out why such examples are outliers and define if any actions needed.· Given anecdotes about anomalies or generate automatic scripts to define anomalies, deep dive to explain why they happen, and identify fixes.· Build decision-making models and propose solution for the business problem you defined· Conduct written and verbal presentation to share insights and recommendations to audiences of varying levels of technical sophistication.· Utilize code (python or another object oriented language) for data analyzing and modeling algorithms.Why you love this opportunityAmazon is investing heavily in building a world-class advertising business. This team is responsible for defining and delivering a collection of advertising products that drive discovery and sales. Our solutions generate billions in revenue and drive long-term growth for Amazon’s Retail and Marketplace businesses. We deliver billions of ad impressions, millions of clicks daily, and break fresh ground to create world-class products. We are highly motivated, collaborative, and fun-loving team with an entrepreneurial spirit - with a broad mandate to experiment and innovate.Impact and Career GrowthYou will invent new experiences and influence customer-facing shopping experiences to help suppliers grow their retail business and the auction dynamics that leverage native advertising; this is your opportunity to work within the fastest-growing businesses across all of Amazon! Define a long-term science vision for our advertising business, driven fundamentally from our customers' needs, translating that direction into specific plans for research and applied scientists, as well as engineering and product teams. This role combines science leadership, organizational ability, technical strength, product focus, and business understanding.Team video https://youtu.be/zD_6Lzw8raE
US, WA, Virtual Location - Washington
The intern will be placed in a large economic team with 10+ full time economists and 3 other interns in the cohort.A day in the lifeTalk with business people to understand business context.Brainstorm with peer economists.Network with other economists and scientists on the team.About the hiring groupThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.Job responsibilitiesThe Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement.Roughly 50% of research assistants from previous cohorts have converted to full time data science or economics employment at Amazon.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, WA, Seattle
Amazon's Product Assurance, Risk and Security (PARS) Team is looking for a smart, energetic, and creative Applied Scientist to apply and extend state-of-the-art research in NLP, probabilistic graphs, knowledge graphs, multi-modal inputs, domain adaptation, meta-learning, and large multi-label hierarchical classification to join the Machine Learning team in Seattle. At Amazon, we are working to be the most customer-centric company on earth. Millions of customers trust us to ensure a safe shopping experience. This is an exciting and challenging position to drive research that will shape new ML solutions for product and food safety, and restricted product compliance in order to achieve best-in-class, company-wide standards around product assurance.You will analyze and process large amounts of tabular, textual, and product image data from historical orders, product detail pages, selling partner details and customer feedback, evaluate state-of-the-art algorithms and frameworks, and develop new algorithms to improve safety and compliance mechanisms. You will partner with engineers and product managers to design new ML solutions implemented across the entire Amazon product catalog.Responsibilities:- Lead and develop other scientists in the team.- Raise the bar for science excellence across PARS- Evaluate state-of-the-art algorithms in NLP, probabilistic graphs, multi-modal inputs, domain adaptation, meta-learning, and large multi-label hierarchical classification- Design new algorithms that improve on the state-of-the-art to drive business impact.- Collaborate with product, UX, and tech partners to experiment new product features in production to automate investigations and increase throughput- Design and plan collection of new labels that allow us to develop better approaches that will further improve product assurance and customer trust.- Analyze and convey results to stakeholders and contribute to the research and product roadmap
US, CA, Palo Alto
As the Director of AI Data Labeling you will lead a geographically distributed, multi-disciplinary team that is responsible for building and operating a scalable, world-class, multi-tenant, high-throughput, high-fidelity data labeling infrastructure. This role requires the ability to lead a team of machine learning (ML) applied scientists, software engineers, statisticians, economists, in-house labelers, product, and program managers. The team builds new software systems, explores new scientific approaches, defines and improves operational processes, and optimizes significant resource investments (people, vendor and compute budgets). The role requires strong operational skills to manage programs and guide product management to consolidate different labeling systems across Search, create a product roadmap that meets the needs of Search and other Amazon Consumer teams, and scale the product while meeting all internal customer needs for labeled data. This role is an opportunity to lead a fast growing area delivering labels for ML applications through a mixture of ML algorithms and human judges. It is an active area of research that will continue to evolve quickly over the next few years and we are looking for a leader at the forefront of this exciting opportunity.
US, WA, Seattle
Entering the business to business (B2B) market is one of Amazon’s most exciting growth opportunities and since launching in 2015, Amazon Business (AB) already has more than 2 million customers. We are growing fast, and require talented data science professionals to help us scale. We at Amazon Business are applying the same entrepreneurial and innovative approach that has made Amazon successful in the ecommerce and software services industry to create an unparalleled shopping experience for business purchasing. We build solutions to enable B2B customers to discover, research, and buy products and services relevant for them. Our customers include individual professionals, small businesses to large institutions (and everything in between) from different industry verticals - across seven countries!To support this vision, we are looking for a Lead Data Scientist supporting Amazon Business (AB) Sales and Marketing business units. As a Data Scientist, you will leverage advanced analytical and machine learning techniques to evolve the way we prioritize customer leads for Sales outreach, improve Sales data quality through experiments including leveraging 3rd party sources, and build hands of the wheel solutions to automatically classify and segment AB customers in suitable categories. As a Data Scientist, you will bring along outstanding analytical abilities and will be comfortable working with cross-functional teams and systems. You must be a self-starter and be able to learn on the go. Some of your key responsibilities include:· · Make recommendations for new metrics, techniques, and strategies to improve methods to prioritize accounts for manual and automated Sales outreach· · Develop machine learning driven algorithms that establish customer personas and deliver tailored suggestions based on customer's purchase behavior and AB journey· · Help Sales and Marketing uncover hidden business opportunities leveraging hard data and advanced analytical techniques· · Work with cross-functional teams including Sales, Marketing, and Product to understand business requirements and build analytical solutions to achieve key business goals· · Collaborate with BI/Data Engineer teams and drive the collection of new data and the refinement of existing data sources to continually improve data quality· · Foster culture of continuous engineering improvement through resource mentoring, feedback, and metricsTo know more about Amazon science, Please visit https://www.amazon.science
US, VA, Arlington
Are you customer-obsessed, data oriented, technologically curious, and eager to propose opportunities to improve the customer experience of using technical Amazon services? We are seeking an experienced, talented, and motivated Data Scientist to join our Technical Customer Experience Strategy team. Our team is dedicated to improving Amazon’s technical products through evaluating the end-to-end customer experience using both internal and external processes and technology. Our team’s mission is to constantly challenge the status quo and drive innovation to improve customer experience. This role specifically focuses on measuring and enhancing the quality of AWS AI services.You will own and drive the roadmap for studying AI quality and build out scalable methods, mechanisms, and tooling to evaluate and deep dive into the quality of AI services. You will engage with AWS AI service teams and leaders to develop scoring methods, identify datasets, evaluate performance, and influence change.Responsibilities:· Ensure data quality throughout all stages of processing, including such areas as data sourcing/collection, ground truth generation, normalization, transformation, cross-lingual alignment/mapping, etc.· Continuously evaluate data analysis tools and processes and offer solutions to ensure they are efficient, high-quality and scalable.· Design, build, and deploy effective and innovative ML solutions to improve various components of the performance measuring stack, such as scoring, trend/pattern analysis, and deep dives.· Develop and improve statistical analyses that provide insights into the business· Communicate analyses and techniques, both verbally and in writing, to peers and business partners.· Evaluate the proposed solutions via offline benchmark tests as well as online A/B tests in production.· Publish and present your work at internal and external scientific venues in the fields of ML.· Present proposals and results in a clear manner backed by data and coupled with actionable conclusions.· Report on the status of projects in a timely and accurate fashion using available metrics.
US, WA, Seattle
Amazon is focused on protecting the health and safety of our employees while continuing to serve people who need our services more than ever. Regular testing on a global scale across all industries would both help keep people safe and help get the economy back up and running. But, for this to work, we as a society would need vastly more testing capacity than is currently available. Unfortunately, today we live in a world of scarcity where COVID-19 testing is heavily rationed.To help solve this problem, Amazon has begun building incremental testing capacity and conducting research and development to apply cutting-edge technology advances to solve testing bottlenecks. We are seeking a Bioinformatics Lead to help define new approaches and execute against scaling them. You will work with a unique and gifted team developing these and collaborate with cross-functional teams. Our team rewards intellectual curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the cutting edge of both academic and applied research in this product area, you have the opportunity to work together with some of the most talented scientists, engineers, and product managers in the field.
US, MA, Cambridge
Want to transform the way people enjoy music, video, and radio? Come join the team that made Amazon Music, Spotify, Hulu, Netflix, Pandora, available to Alexa customers. We are innovating the way our customers interact with entertainment in the living room, on the go, and in the car. We are at the epicenter of the future of entertainment.Alexa Entertainment is looking for an Applied Scientist as we build a team of talented and passionate scientists for ASR (automatic speech recognition) and NLU (natural language understanding). As an Applied Scientist, you will participate in the design, development, and evaluation of models and ML (machine learning) technology so that customers have the magical experience of entertainment via Alexa. You will help lay the foundation to move from directed interactions to learned behaviors that enable Alexa to proactively take action on behalf of the customer. And, you will have the satisfaction of working on a product your friends and family can relate to, and want to use every day. Like the world of smart phones less than 10 years ago, this is a rare opportunity to have a giant impact on the way people live.You will be part of a team delivering features that are highly anticipated by media and well received by our customers.
US, WA, Seattle
Are you passionate about leveraging your economics/econometrics skills and data to deliver actionable insights that impact daily business decisions at Amazon? Do you like getting "scrappy" with data and applied economics tools to answer challenging product and customer behavior questions? Do you enjoy building flexible, performant, and global solutions for complex financial, risk, and causal inference problems? If so, here is a great opportunity to consider!A day in the lifeAmazon B2B Payments is seeking a thoughtful Economist who combines their causal inference expertise with business intuition to generate critical insights that will set the strategic direction of the business. As an Economist on the Credit Systems Research team, you will design and build systems/solutions that support financial products, working closely with business partners, product partners, and engineers. Your work will focus on Amazon Lending, which offers loan products to help small and medium-sized businesses grow on Amazon. You will utilize causal inference and experimentation methodologies, data and coding skills, problem solving and analytical skills, and excellent communication to deliver customer value.About the hiring groupThe mission of B2B Payments is to create trusted paying experiences and financial services that empower any business to engage with Amazon from anywhere in any way. Within B2B Payments, the Credit Systems team builds models and systems to maximize business growth and customer experience/value while achieving risk constraints.Job responsibilitiesYou will support our causal analysis and experimentation workstreams. You will use novel and advanced causal economics/econometrics techniques to answer questions on a number of challenging business questions related to credit systems products, focusing on Amazon Lending. You will be responsible for researching insights as well as educating the business, product, marketing, and business development teams on the implementation of those insights to enable data-driven decision making. You will partner with our product management, finance, marketing, engineering, and operations teams to:· Contribute to the development and enhancement of business payment products and features.· Use observational as well as experimental data to develop empirical econometric analysis and models to drive the business and improve our causal inference workstream.· Understand business and product strategies, goals, and objectives and help set the causal and experimental roadmap.· Analyze and solve problems at their root, stepping back to understand the broader context.Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
US, CA, Glendale
The Amazon Web Services (AWS) Center for Quantum Computing in Pasadena, CA, is looking to hire a Quantum Research Scientist with expertise in implementing, characterizing and validating coherentcontrol techniques for quantum information processing. Working alongside physicists and engineers, you will use your coherent control knowledge to help develop and implement novel multi-qubit control protocols. You will then use your experimental experience as you characterize, verify and validate their performance on qubit processors. Responsibilities include, but are not limited to:· using control theory, device physics, and quantum information concepts as necessary to develop and debug control/characterization protocols· numerical simulation of protocols on multi-qubit systems to inform experiments· converting protocols to experimental reality using a mixture of commercial and custom hardware· contributing experimental routines and data analysis to the control software codebase· developing statistically valid data analysis routines to distill the data into plainly communicable results to a multi-disciplinary teamWork/Life BalanceAt the AWS CQC, we understand that developing quantum computing technology is a marathon, not a sprint. Mental and physical wellness is encouraged within our team and throughout AWS. The work/life integration within Amazon encourages a culture where employees work hard and have ownership over their downtime. We are exploring more structured wellness elements including meditation scheduling, running group meet-ups, and a culture of sharing wellness tips.Mentorship and Career GrowthWe are committed to the growth and development of every member of the Center for Quantum Computing. You will receive career-growth-minded management and mentorship from a software and science team and also have the opportunity to participate in Amazon's mentorship programs. You will work closely with quantum research scientists and have opportunities to learn about quantum computing technology and contribute to the development of scientific software for quantum computing at AWS.Inclusive and Diverse CultureThe AWS CQC is intentional about attracting, developing, and retaining amazing talent from diverse backgrounds to build a world class team. We’re looking for a new teammate who is enthusiastic, empathetic, curious, motivated, reliable, and able to work effectively with their peers. With quantum computing being a new and growing initiative within AWS, you would have an opportunity to make an impact on our budding team culture.Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation
US, NY, New York
The Automated Reasoning Group in AWS Platform is looking for an Applied Scientist with experience in building secure, scalable solutions that delight customers. You will be part of a world-class team building the next generation of automated reasoning tools and services. You will apply your knowledge to propose 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. You have strong verbal and written communication skills, are self-driven and deliver high quality results in a fast-paced environment.Each day, hundreds of thousands of developers make billions of transactions worldwide on AWS. They harness the power of the cloud to enable innovative applications, websites, and businesses. Using automated reasoning technology and mathematical proofs, AWS allows customers to answer questions about security, availability, durability, and functional correctness. We call this provable security, absolute assurance in security of the cloud and in the cloud. https://aws.amazon.com/security/provable-security/As an applied scientist on team, you will play a pivotal role in shaping the definition, vision, design, roadmap and development of product features from beginning to end. You will:· Research algorithms in code-level automated reasoning involving the Rust and C languages to scale automated proofs of AWS code· Design, implement, test, deploy and maintain innovative software solutions to transform service performance, durability, cost, and security· Use software engineering best practices to ensure a high standard of quality for all of the team deliverables· Prove properties of business-critical software and systems software· Work in an agile, startup-like development environment, where you are always working on the most important stuff· Work with the team to help drive business decisionsAWS 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.This role can be based in Boston, NYC, Seattle, Bay Area, and other major cities.Mentorship & Career GrowthWe 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 DiversityOur 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.Work/Life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.This position involves on-call responsibilities, typically for one week every two months. We don’t like getting paged in the middle of the night or on the weekend, so we work to ensure that our systems are fault tolerant. When we do get paged, we work together to resolve the root cause so that we don’t get paged for the same issue twice.
US, WA, Seattle
Amazon is looking for an outstanding Data Scientist to join the AWS Product Analytics team. This is your opportunity to be a core part of the team that has direct impact on affecting the long term roadmap of the AWS EC2 Product Team. This role is within a larger Data science, Business Intelligence & Data engineering team that focuses on broad data exploration, quantitative methodology, and statistical modeling to drive actionable data intelligence in AWS.Since early 2006, AWS has provided companies of all sizes with an infrastructure platform in the cloud. AWS is a high-growth, fast-moving division within Amazon with a start-up mentality where new and diverse challenges arise every day. On the AWS Product Analytics team you will be surrounded by people that are exceptionally talented, bright, and driven, and believe that world class Data Science is critical to our success. To help build this growing team, you must be highly analytical and possess a strong passion for analytics and accountability, set high standards with a focus on superior business success. We take working hard, having fun, and making history seriously. AWS sets the standard for functionality, cost, and performance for many cloud based services, but it’s still early days for cloud computing, and there are boundless opportunities to continue to redefine the world of cloud computing - come help us make history!As a Data Scientist, you will discover and solve real world problems by analyzing large amounts of business data, defining new metrics and business cases, designing simulations and experiments, creating models, and collaborating with colleagues in business, software, and research. You will get the exciting opportunity to work on some of the world’s largest and diverse datasets. The successful candidate will have a strong quantitative background and can thrive in an environment that leverages statistics, machine learning, operations research, econometrics, and business analysis.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 host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.Work/Life BalanceOur team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.Mentorship & Career GrowthOur team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, NH, Virtual Location - New Hampshi
The Amazon Device and Services Design Group (DDG) creates revolutionary products used by millions of customers around the world every day - including Echo, Fire TV, Alexa Communications, and more. Within DDG, the DDG Research team is one of the behind-the-scenes teams that enables Amazon’s Devices’ leaders to make informed decisions based on sound mixed-method research and analytics. We are seeking an exceptional Research Scientist to join our team to help us derive insights that serve our customers. If you are inquisitive, passionate about how research can improve decision making, enjoy weaving data into a telling story, and like your research to have real world impact, we want you on our team.As a successful Research Scientist, you:· Are enthusiastic about collaborating with a cross-functional team of UX designers, researchers (qualitative and quantitative), business partners, design technologists, and developers to provide actionable insights.· Demonstrate excellent statistical skills and are excited about learning new methods.· Are naturally curious about people, especially their motivations, attitudes, and behaviors.· Excel when interacting with business and technical partners whether you are chatting, sending a written message, writing a technical report, or conducting a presentation.· Enjoy working with stakeholders to define their key business needs and deliver on those commitments.· Innovate on behalf of your customers by proactively implementing improvements and taking steps to address challenges that they had not yet identified.· Are drawn to ambiguous, complex problems.· Surface and question both your own and others’ underlying assumptions.· Persuade decision makers at all levels of the organization to take aligned action on research findings – inspire and help them internalize opportunities to delight our customers and differentiate our service.· Define, execute, and invent research methods appropriate to the questions at hand, including but not limited to field research, surveys, lab studies, remote testing, and A-B tests.
US, PA, Pennsylvania
The Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata or R is necessary, and experience with SQL, UNIX, and Sawtooth would be a plus.These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement.Roughly 50% of research assistants from previous cohorts have converted to full time data science or economics employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation