Careers

Come join the AWS Agentic AI science team in building the next generation models for intelligent automation. AWS, the world-leading provider of cloud services, has fostered the creation and growth of countless new businesses, and is a positive force for good. Our customers bring problems that will give Applied Scientists like you endless opportunities to see your research have a positive and immediate impact in the world. You will have the opportunity to partner with technology and business teams to solve real-world problems, have access to virtually endless data and computational resources, and to world-class engineers and developers that can help bring your ideas into the world. As part of the team, we expect that you will develop innovative solutions to hard problems, and publish your findings at peer reviewed conferences and workshops. We are looking for world class researchers with experience in one or more of the following areas - autonomous agents, API orchestration, Planning, large multimodal models (especially vision-language models), reinforcement learning (RL) and sequential decision making. Key job responsibilities * Define and implement new automated reasoning features that employ scalable and efficient approaches to solve complex problems using neural learning and symbolic/formal reasoning * Apply software engineering best practices to ensure a high standard of quality for all team deliverables * Work in an agile, startup-like development environment * Deliver high-quality scientific artifacts * Work with the team to help drive business decisions About the team About the team Why AWS? AWS is the world’s most comprehensive and broadly adopted cloud platform. We pioneered cloud computing and never stopped innovating — that’s why customers from the most successful startups to Global 500 companies trust our robust suite of products and services to power their businesses. Inclusive Team Culture Here at AWS, it’s in our nature to learn and be curious. Our employee-led affinity groups foster a culture of inclusion that empower us to be proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon conferences, inspire us to never stop embracing our uniqueness. Mentorship & Career Growth We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional. Work/Life Balance We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why we strive for flexibility as part of our working culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve in the cloud.

Amazon is seeking a motivated candidate to provide insights into opportunities for operational improvement through analytics. Role will require analysis, understanding of the systems workflow, cross-functional communication and issues management. The successful candidate is passionate about optimizing business processes and performance metrics, and takes a driven approach to identifying and prioritizing the most impactful efforts. This role will also build tools and support structures needed to analyze, dive deep to determine root cause of system errors, network changes and performance issues. This role will need to present findings to business partners to drive improvements and prioritize customer needs to deliver the right results. Key job responsibilities · Design and implement scalable and reliable approaches to support or automate decision making throughout the business. · Apply a range of science techniques and tools combined with subject matter expertise to solve difficult business problems and cases in which the solution approach is unclear. · Build using statistical, mathematical, econometric, network, natural language processing, machine learning algorithms, genetic algorithms, and neural networks. · Acquire by building the necessary / ETL queries. · Establish scalable efficient, automated processes for large scale analyses, development, validation and implementation. · Analyze for trends and input validity by inspecting univariate distributions, exploring bivariate relationships, constructing appropriate transformations, and tracking down the source and meaning of anomalies. · Validate against alternative approaches, expected and observed outcome, and other business defined key performance indicators. · Implement that comply with evaluations of the computational demands, accuracy, and reliability of the relevant ETL processes at various stages of production. · Build relationships with stakeholders and counterparts.

Fulfillment by Amazon (FBA) is a service that enables sellers to outsource supply chain and fulfillment to Amazon and use Amazon's world-class science, technology, and logistics infrastructure to deliver billions of products from manufacturing hubs to customers worldwide with fast delivery promise. As FBA expands into end-to-end supply chain and fulfillment management, the science problems are growing in complexity and strategic importance. The FBA organization is looking for a Principal Applied Scientist with deep expertise in Operations Research, Reinforcement Learning, and strong modeling and analytical skills to join our cross-domain group of applied scientists, research scientists, economists, and data scientists building the intelligence layer for FBA's supply chain. As a lead Principal Applied Scientist, you will own the science strategy and execution for the optimization algorithms that power FBA's supply chain, spanning the full journey from the moment a seller procures product at origin, through upstream warehousing and distribution, and into Amazon's fulfillment network. Working with a team of scientists, your technical challenges will span product selection optimization for capacity-constrained speed nodes, balancing demand coverage, profitability, and speed sensitivity across hundreds of sites; multi-echelon inventory optimization across a tiered architecture spanning origin-country warehousing, destination-country distribution centers, and regional fulfillment centers; auction mechanisms that allocate scarce capacity to sellers efficiently; seller recommendation systems that deliver explainable, economically quantified guidance; and adoption of frontier AI approaches to accelerate science delivery across the team. Your work will directly shape how millions of products flow from factory floor to customer door for millions of sellers, and your algorithms will determine the economic viability of Amazon's fastest-growing fulfillment investments. We are looking for a seasoned scientist who brings rigorous operations research thinking to large-scale supply chain problems, and who thrives in the ambiguity of defining the roadmap rather than receiving it. The problems above also draw on reinforcement learning for sequential, non-stationary decisions; machine learning for the prediction and estimation layer; and mechanism design for incentive design and auctions. Beyond individual contribution, you will set the long-term technical vision across work streams, influence product managers, engineers, scientists, and senior leaders on high-judgment decisions, and mentor junior scientists. We value deeply technical people who deliver results incrementally and frequently in a fast-paced, high-energy environment, and who are eager to learn new areas and develop themselves and their colleagues. Key job responsibilities - Own the science strategy and development of inventory routing, replenishment, product selection, mechanism design, and transportation distribution algorithms that power FBA's supply chain across Amazon's fulfillment network. - Design and implement large-scale optimization algorithms and incentive-compatible mechanisms for marketplace challenges, including auction design and pricing strategies. - Partner with Product Managers and Software Engineers to translate ambiguous business challenges into well-scoped science initiatives, and build and deploy production-grade solutions that operate reliably at scale across a network serving millions of sellers. - Influence senior leaders on technical and business direction, identify and propose new science investment areas, and represent the science perspective across organizations. - Mentor and develop junior scientists, raise the technical bar for the broader science community, and drive adoption of emerging research methods across the team. A day in the life In this role, you will be a technical leader in operations research and optimization with significant scope, impact, and high visibility. Your solutions will lead to billions of dollars of impact on either the topline or the bottom line of Amazon's third-party seller business. You will work closely with Product Managers, Software Engineers, and other Scientists to deeply understand FBA seller business problems and priorities. You will design and launch new systems, solving real-world inventory, transportation, replenishment, pricing, and mechanism design problems with millions of unique products involving hundreds of thousands of Selling Partners and tens of millions of customers around the world. As a scientist on the team, you will be involved in every aspect of the process — from idea generation, business analysis, and scientific research, through to development and deployment of production-grade optimization models — giving you a real sense of ownership. You are expected to make decisions about methodology, model architecture, and technology choices, striving for simplicity and judgment backed by mathematical rigor. You will also collaborate with the broader decision and research science community at Amazon to broaden the horizon of your work and mentor scientists. About the team Sellers play a vital role in Amazon’s ecosystem, integral to our mission of offering the Earth’s largest selection, lowest prices, and fastest delivery speed. FBA is an optional service that enables third-party sellers to outsource order fulfillment to Amazon, and leverage Amazon’s world-class facilities to provide customers fast delivery promise. With commitment to taking on even more of the supply chain and operational complexities on behalf of our selling partners, Amazon now provides an end-to-end suite of supply chain and fulfillment services. This comprehensive solution empowers sellers to reliably transport products from manufacturing sites to customers worldwide. The FBA team is the core group in charge of warehousing, inventory management, fulfillment and pricing, and a diverse range of recommendation services for sellers, as well as building the internal resource management systems. We work to learn seller behavior, understand seller experience, recommend right actions to sellers, design seller policies and incentives, and develop science products and services that empower sellers to grow their businesses. To do so, we build and innovate science solutions that leverage the right tools across different fields including operations research, economics, machine learning, statistics, and data analytics. Our culture is centered on rapid prototyping, rigorous experimentation, and data-driven decision-making. We are open to hiring candidates to work out of one of the following locations: Bellevue, WA, or Sunnyvale, CA.

Do you want to join an innovative team of scientists and engineers who use terabytes of data and create state-of-the-art Generative AI algorithms to push the boundaries of AI creativity? We are building foundational behavioral models for Amazon Stores using Generative AI, LLMs and Large Model training techniques that fuses general world knowledge, customer shopping behavior and Amazon e-commerce domain knowledge. We are looking for scientists who are passionate about technology, innovation, and customer experience, and are ready to make a lasting impact on the industry using intelligent and transformative AI applications. Working closely with cross-functional teams, you will be an essential part of every stage of AI development, from ideation and design to rigorous testing and successful deployment, ensuring our AI projects drive innovation and provide value for our customers. If you’re fired up about being part of a dynamic, driven team, then this is your moment to join us on this exciting journey! Key job responsibilities In this role you will leverage your background and expertise to lead developing foundational behavioral model for Amazon Stores using Generative AI, LLM and Large Model training techniques. On a day-to-day basis, you will: - Research and implement new algorithms and architectures for generative AI applications. - Optimize model performance and scalability for inference and deployment. - Collaborate with other talented applied scientists and engineers to gather and preprocess large datasets and develop an improved training infrastructure that accelerates innovation. - Experiment with SOTA methods to improve generative AI model quality. - Provide technical expertise and guidance to support the integration of generative AI solutions into various products and services.

Amazon Music is an immersive audio entertainment service that deepens connections between fans, artists, and creators. From personalized music playlists to exclusive podcasts, concert livestreams to artist merch, Amazon Music is innovating at some of the most exciting intersections of music and culture. We offer experiences that serve all listeners with our different tiers of service: Prime members get access to all the music in shuffle mode, and top ad-free podcasts, included with their membership; customers can upgrade to Amazon Music Unlimited for unlimited, on-demand access to 100 million songs, including millions in HD, Ultra HD, and spatial audio; and anyone can listen for free by downloading the Amazon Music app or via Alexa-enabled devices. Join us for the opportunity to influence how Amazon Music engages fans, artists, and creators on a global scale. Learn more at https://www.amazon.com/music. The Music Catalog Quality team at Amazon Music serves a key role in developing solutions to ensure and improve the quality of catalog metadata and content across the music streaming experience. We create solutions that detect, measure, and remediate quality issues in music metadata - including artist information, track attributes, versions, content tags, and provide actionable insights that enable continuous improvement of the catalog. We leverage a host of scientific and engineering technologies to accomplish this mission, including Generative AI, classical ML, Natural Language Processing, Computer Vision, and automated data validation pipelines. Key job responsibilities As an Applied Scientist, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. Other responsibilities include: - Collaborate with scientists, engineers, and product managers to define and frame business problems as ML or optimization tasks. - Use machine learning, deep learning, LLMs and Agentic AI techniques to create scalable solutions for business problems - Analyze and extract relevant information from large amounts of Amazon's data to help automate and optimize key processes - Design, development and evaluation of AI models for predictive learning - Research and implement novel machine learning and statistical approaches - Implement scalable data pipelines and model-serving systems. - Analyze experimental results, draw insights, and refine models to improve accuracy and robustness. - Communicate findings and recommendations to technical and non-technical audiences.

Amazon Ads is a multi-billion dollar global business that delivers advertising experiences across Amazon's owned-and-operated properties (including Prime Video, Twitch, Fire TV, and Amazon.com), third-party publisher networks, and emerging channels like generative AI-powered shopping experiences. As one of the fastest-growing segments of Amazon, we operate at unprecedented scale across desktop, mobile, connected TV, and emerging surfaces. Within Amazon Ads, Traffic Quality is a critical pillar of advertiser trust and marketplace integrity. Our mission is to build advanced capabilities that work at petabyte scale to detect sophisticated invalid traffic (IVT) which includes sophisticated non-human traffic, bot networks, and fraudulent engagement patterns across programmatic advertising. We are on a journey to establish Amazon Ads as an industry leader in traffic quality standards and transparency. Our research agenda focuses on staying ahead of adversarial actors through continuous innovation in detection methodologies, leveraging state-of-the-art techniques in deep learning and generative modeling, user behavior and multi-modal representation learning, anomaly detection, time-series analysis, and sparse labeling methods. We process billions of ad events daily, developing novel algorithms that balance precision and recall while operating under strict latency constraints. Our work directly protects hundreds of millions of dollars in advertiser spend annually while maintaining a seamless user experience. Key job responsibilities Strategic Leadership & Vision - Define long-term science vision for Traffic Quality driven by advertiser and publisher needs, translating direction into actionable team plans. - Solve strategically important business problems independently, delivering robust, scalable scientific solutions with limited guidance. - Proactively identify technology gaps and business opportunities, determining resource allocation priorities. Scientific Innovation & Execution - Design and implement statistical and machine learning solutions to detect robotic and human traffic patterns across billions of daily ad events. - Own full development cycle for production-level code handling billions of ad requests: design, prototype, A/B testing, and deployment. - Stay current with scientific advancements and build publication strategy while championing excellence best practices. - Directly protect hundreds of millions of dollars in advertiser spend annually while maintaining seamless user experience. - Partner with engineers, product managers, and cross-functional teams to solve complex IVT detection problems and influence strategic initiatives. - Mentor scientists on the team. About the team Here are a few papers published by the team: 1/ [Scaling Generative Pre-training for User Ad Activity Sequences. AdKDD 2023.](https://assets.amazon.science/b7/42/03be071743d5a57cb1656e6caa34/scaling-generative-pre-training-for-user-ad-activity-sequences.pdf) 2/ [SLIDR: Real-time Robot Detection On Online Ads, IAAI 2023, Deployed Highly Innovative Applications of AI Track (AAAI 2023)](https://assets.amazon.science/75/2f/3b7106b143f38f7f4d2806388ace/real-time-detection-of-robotic-traffic-in-online-advertising.pdf) 3/ [Self-supervised Representation Learning Across Sequential and Tabular Features Using Transformers, NeurIPS 2022, First Table Representation Learning Workshop](https://openreview.net/forum?id=wIIJlmr1Dsk)

Some CX shopping defects might be straightforward to detect and track. The interesting ones are not because they depend on what a customer perceives. For example, a search page may return legitimately different results, yet a shopper has no way to tell apart. We turn these ambiguous perception questions into a measurable artifact using LLMs, and we build the frameworks to know exactly where model judgment can be trusted and where a human must decide and proving it, against ground truth, at Amazon scale. This is one example of an LLM based measurement pipeline you will own, but that’s not all. You will extend that measurement to other parts of the shopping experience like the homepage and the detail page, where the same customer problem looks nothing like it does in search results, and where you will design the measurement from scratch. The larger goal is what makes this role unusual. Teams across Amazon are each independently figuring out how to label quality with LLMs, hitting the same problems alone: prompts that break on the next model version; golden sets nobody audited, accuracy that collapses in other locales. Through the work above, you will set the standard and build the production tooling behind it. Reusable labeling pipelines, evaluation frameworks, and inference infrastructure that hold up against Amazon-sized data and get adopted by teams who did not have to use them. Key job responsibilities - Design and improve LLM-based labeling for perception-driven defects: prompt design, sampling strategy, and the split between model judgment and human annotation. - Validate labeling quality against human ground truth, and build and maintain the golden datasets that make that validation possible. - Extend perceived-duplicate measurement to other parts of the shopping experience, designing the methodology where none exists and evaluating approaches already in use where one does. - Build reusable, production-grade labeling and evaluation tooling, batch inference, quality sampling, prompt and model version control, that operates on Amazon-scale data. - Define and publish the standards other teams adopt for using LLMs to measure customer experience. - Partner with science, engineering, and product teams across Stores to make quality measurement usable in their decisions, and present metric results and methodology changes to stakeholders. A day in the life We are a small team, which means your work is visible and your scope grows as fast as you do. There are existing partnerships with other teams and a paved way to cross org influence.

Every day, hundreds of millions of customers arrive on Amazon's Homepage, search for a product, and land on a detail page. Along the way, some of what we show them is irrelevant — a recommendation that misreads what they want, a widget that repeats what they just saw, a headline that doesn't say what it means, a product that shouldn't have been surfaced at all. We have built the ability to detect these defects at scale using Large Language Models (LLMs), and we report them to Amazon's most senior leadership as a company-level measure of shopping quality. What we have not yet built is the confidence to act on every one of them. That is the problem you will own. Today, the most consequential categories of shopping defects — product quality, duplication, staleness, irrelevance — go largely unenforced. Not because we cannot detect them, but because we have not yet clearly defined when they lead to customer dissatisfaction. These are genuinely hard questions. When is a recommendation irrelevant rather than merely unexpected? When are two products duplicates rather than legitimate alternatives? Every answer carries consequences for customers and advertisers. As Principal Data Scientist, you will own the analytical rigor behind Amazon's store quality metrics end-to-end: how they are defined, how faithfully our LLM implementations execute those definitions, and how accurate the resulting judgments actually are across relevance, presentation, product quality, and duplication. You will go deep enough to inspect individual model judgments and read the edge cases where they break, then come back up to argue definitional questions with the leaders who own the outcomes on both sides. You will also define experiments that will turn judgement into facts backed by data. Your influence will come from deep dives so well-constructed that stakeholders across two large organizations change their minds. Getting there means building the tooling that makes rigor repeatable rather than heroic: agents that walk the store the way a customer would, automated inspection of experiments, and feedback loops that finally connect what customers tell us directly to the metrics we optimize. Much of the customer voice we already collect goes underused today; you will change that. You will begin on the Homepage, where measurement is most mature, then extend the methodology to Detail Page and Search — carrying not just the metrics but the standard of evidence with them. Key job responsibilities - Validate store quality metrics end-to-end: inspect metric definitions, audit LLM implementations, and evaluate LLM judgment accuracy across quality dimensions (relevance, presentation, product quality, duplicates) - Starting with Homepage, extending cross-page — identify gaps and inconsistencies between Organic and Ads treatments that block the tiered enforcement framework - Drive alignment through deep dives that present evidence to both Stores and Ads stakeholders - Build and deliver deep-dive tooling (walk-the-store bots, automated experiment inspection via Gecko, VoC feedback loops) that make metric validation repeatable and self-serve - Own the analytical rigor behind the alignment on definitions of subjective/debated metrics and moving them to aligned/enforceable About the team Core Shopping Data Science owns the measurement of shopping quality across Amazon's Core Shopping eexperiences, including defect metrics reviewed by Amazon's most senior leadership. We focus on the long term and big picture to ensure that the full Amazon shopping experience balances strategic trade-offs. We work across Stores and Advertising, partnering with personalization, ranking, and search teams to turn measurement into changes customers can feel.

Alexa International is looking for a passionate, talented, and inventive Applied Scientist to help build industry-leading technology with Large Language Models (LLMs), ASR, TTS, and Speech to Speech models, requiring strong deep learning and generative models knowledge. You will contribute to developing novel solutions and deliver high-quality results that impact Alexa's international products and services. Key job responsibilities As an Applied Scientist with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with Large Language Models (LLMs), ASR, TTS, and Speech to Speech model. Your work will directly impact our international customers in the form of products and services that make use of digital assistant technology. You will leverage Amazon's heterogeneous data sources, unique and diverse international customer nuances and large-scale computing resources to accelerate advances in text, voice, and vision domains in a multimodal setup. The ideal candidate possesses a solid understanding of machine learning, natural language understanding, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environments to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and collaborate effectively with cross-functional teams. A day in the life * Analyze, understand, and model customer behavior and the customer experience based on large-scale data. * Build novel online & offline evaluation metrics and methodologies for multimodal personal digital assistants. * Drive research in ASR, TTS, and Speech-to-Speech (S2S) model training and fine-tuning * Advance multilingual speech recognition and synthesis using LLM-based architectures * Fine-tune/post-train LLMs using techniques like SFT, DPO, RLHF, and RLAIF. * Collaborate with partner teams on evaluation frameworks and post-training methodologies. * Communicate solutions clearly to partners and stakeholders. * Contribute to the scientific community through publications and community engagement.

As an Applied Scientist on the Science SW team, you will be a versatile generalist who collaborates closely with other scientists and engineers teams to bring research to production across a broad portfolio of problems: from computer-vision perception platforms to building-wide optimization and orchestration. This role combines the scientific application of ML and applied mathematics with a strong product focus. It will be your job to frame ambiguous business problems as tractable scientific problems, and to implement novel ML systems, first-principles models, embedded systems prototypes, and performance optimizations in both prototype and production environments. Key job responsibilities • Own the research and development of scientific and ML solutions across a broad range of problems spanning classical machine learning, statistical modeling, computer vision, optimization, and physics-informed / first-principles modeling in a production environment. • Rapidly ramp on unfamiliar problem domains, frame ambiguous or open-ended business problems as tractable scientific problems, and prototype solutions end to end. • Prototype and evaluate sensing hardware and lightweight, edge-deployable models that run on commodity compute under real-world constraints. • Collaborate across multiple science and engineering teams to integrate your solutions into our deployment architecture. About the team Amazon is building next generation software, hardware, and processes that will run our global network of fulfillment centers that move millions of units of inventory, and ensure customers get what they want when promised. The Science Software team in the One MHS organization unlocks Material Handling Equipment (MHE) innovation through a multiplicity of disciplines within Artificial Intelligence (AI) and applied science, including Computer Vision (CV), Physics-Informed Neural Networks (PINNs), Optimization, Reinforcement Learning, classical Machine Learning, statistical modeling, and sensing-hardware prototyping. Rooted in first principles aligned experimentation, the team is dedicated to building self-optimizing fulfillment centers, developing the models that drive real-time, building-wide orchestration of MHE. We conduct experiments, develop models, and apply machine learning (ML) at scale to optimize throughput, flow, merge, and congestion control, and to improve operational performance across the fulfillment network.