Automated evaluation of RAG pipelines with exam generation

The fight against hallucination in retrieval-augmented-generation models starts with a method for accurately assessing it.

In the swiftly evolving domain of large language models (LLMs), the accurate evaluation of retrieval-augmented-generation (RAG) models is paramount. In this blog, we introduce a pioneering methodology that employs an automated exam generation process, enhanced by item response theory (IRT), to evaluate the factual accuracy of RAG models on specific tasks. Our approach is not only robust and interpretable but also cost efficient, strategically identifying model strengths and refining exams to optimize their evaluative utility. We describe our methodology in a paper we will present in July at the 2024 International Conference on Machine Learning (ICML).

Exam generation process

RAG is a method for handling natural-language queries by retrieving relevant documents and using text from them to seed the response generated by an LLM. The expectation is that factual assertions from reliable documents will curb the LLM’s tendency to “hallucinate”, or generate reasonable-sounding but false sentences.

To evaluate a RAG model on a particular task, we use an LLM to generate multiple-choice questions from a task-specific knowledge corpus. Our method is agnostic to the retriever and generative model used in both the RAG system and the exam generation task.

RAG diagram.png
Summary of the proposed exam generation, evaluation, and iterative-improvement processes.

Our approach has two steps. For each document in the knowledge corpus, we use an LLM and several prompt-engineering strategies to create candidate questions. Then we use several natural-language-processing filters to remove low-quality questions along various axes, such as length, incorrectness, and self-containment.

We note an interesting asymmetry: given a document corpus, it is relatively easy for an LLM to generate a question and the correct answer, as the content of both is contained in the prompt. However, it is considerably more difficult to create high-quality incorrect answers, commonly referred to as discriminators.

To filter out degenerate questions, we use the Jaccard similarity coefficient and embedding-based similarity metrics.

Here is the prompt that we used for exam generation:

Human: Here is some documentation from {task_domain}: {documentation}.\n
From this generate a difficult multi-form question for an exam.
It should have 4 candidates, 1 correct answer, and explanations.

Syntax should be Question: {question}\n
A){candidate A}\n
B){candidate B}\n
C){candidate C}\n
D){candidate D}

Correct Answer: {correct answer}\n
### Assistant:"

In our research, we analyzed several RAG pipeline variants, including closed-book (no knowledge from the document corpus is provided to the LLM), oracle (the exam taker has access to the specific document used to generate the question-and-answer pair, in addition to the question itself and all possible candidate answers), and classical retrieval models such as MultiQA embeddings, Siamese network embeddings, and BM25. Our evaluations also extended to different scales of language models, from 7 billion parameters to 70 billion, to understand the impact of model scale on performance.

To demonstrate the practical utility of this methodology, we deployed it across a wide range of domains. These include Amazon Web Services (AWS) DevOps, where troubleshooting guides for cloud-based services tests the models' operational effectiveness; arXiv abstracts, which challenge the models' ability to parse and generate insights from dense scientific texts; StackExchange questions, which probe the models' responsiveness and accuracy; and SEC filings, where the complexity of financial reporting tests the models’ capacity to extract nuanced information from structured corporate documents. This multi-domain approach not only enhances the robustness of our evaluations but also ensures that our models are versatile and reliable across various real-world applications.

Evaluating the exam generation model

The following figure shows granular results of our evaluation method for the task of AWS DevOps troubleshooting. We report accuracy for different retrieval approaches and retriever sizes, on a percentage scale. Labels on the diameter show the AWS resources we’re using. Colors correspond to different retrieval approaches (Oracle, DPRV2, MultiQA, ClosedBook), and solid and broken lines correspond to different base LLM sizes (7B, 13B, and 70B). For instance, we observe that a small model such as Mistral-7B with MultiQA embeddings has an accuracy of around 80% for the AWS resource Relational Database Service (RDS).

Granular results of our exam evaluation for the task of AWS DevOps troubleshooting.png
A comparison of several different models, at a range of sizes, on the task of DevOps troubleshooting for eight different AWS resources.

Our experiments yielded four key findings. First, there’s no one-size-fits-all solution; the optimal choice of retrieval method, and to a lesser extent LLM, is typically task dependent. For example, in tasks such as SEC filings and arXiv abstracts, BM25 outperforms MultiQA and Siamese network embeddings, indicating that sparse retrieval is generally more effective than dense retrieval. This could be because such tasks often contain easily identifiable terms (e.g., AWS service names in AWS DevOps) that can be retrieved with keyword search, while other tasks, such as StackExchange, mostly contain common words.

Second, the right choice of retrieval method can lead to greater performance improvements than simply using larger LLMs. For instance, in SEC filings, we observed a greater performance gain from switching from Siamese network embeddings to DPRV2 than from switching to larger LLMs.

Third, for tasks involving closed-source knowledge, the accuracy bottleneck is typically the LLM rather than the retrieval method. Finally, a poorly aligned retriever component can result in worse accuracy than having no retrieval at all.

Exam enhancements through item response theory

Integrating item response theory (IRT) into our process has significantly improved the quality of the exams. IRT models the likelihood of a correct response based on characteristics of a question and the capabilities of a model. It uses three factors — difficulty, discrimination, and guessing chance — to create exams that more accurately reflect and predict model performance.

IRT posits that a model’s probability of correctly answering a question is correlated with a latent variable known as ability, and it provides a method for estimating the value of that variable. As such, it offers a way to quantify a model’s ability level.

Our process begins with an initial exam assessment, identifying and removing questions that contribute minimally to discriminative insights. The exam is then refined iteratively, based on updated IRT parameters, which helps it accurately gauge nuanced model behaviors.

By continuously analyzing and adjusting exams based on IRT parameters, we have seen substantial improvements in the exams’ ability to discriminate among models. For instance, we use Fisher information to quantify the informativeness of exam questions. Fisher information measures the amount of information that an observable random variable provides about an unknown parameter, offering a way to gauge the precision of statistical estimators in parameter estimation theory.

During iterative improvements for the arXiv task, the Fisher information function consistently showed progress, marking a considerable enhancement of the exams' capacity to differentiate model capabilities. This iterative process ensures that each new version of the exam is more informative than the last and effectively evaluates the RAG model’s abilities.

Evaluating the generated exams

To further enhance the assessment of RAG models, we categorize exam questions using both semantic analysis and Bloom’s revised taxonomy, devised by the University of Chicago psychologist Benjamin Bloom. Bloom’s taxonomy helps classify questions by cognitive complexity — from basic recall to analytical tasks — enabling structured evaluation of model capabilities.

Different levels in Bloom's taxonomy differentiate between the knowledge dimension (factual, conceptual, procedural, and meta-cognitive) and the cognitive-process dimension (remember, understand, apply, analyze, evaluate, and create). Additionally, we classify questions semantically by identifying keywords like “what” and “which.” These additional classifications allow us to assess how well models perform at different ability levels.

Bloom's Taxonomy.png
Average Fisher information for each category in Bloom’s taxonomy category (left) and semantic category (right) for the StackExchange task.

The above two figures present the average Fisher information value for each Bloom category (left) and semantic category (right) for the StackExchange task. For this specific task, we observe that “evaluating” and “understanding” are the most discriminate dimensions in Bloom’s taxonomy across different ability levels, while “remembering” is the least discriminatory.

On the semantic categories, we observe that “what” and “which” were the most discriminatory terms for lower ability levels, and “when” discriminated more at higher ability levels. One interpretation is that “what” and “how” questions tend to be more factual and syntax-based in the StackExchange domain, so at lower ability levels, RAG struggles more with these genres of questions.

The following figure illustrates the maximization process for the arXiv task as the exam and IRT estimation evolve. We show the results for three incremental steps. We observe a 0.05 increase in Fisher information even with a single iteration. This progress reaches a 0.1 increase in the subsequent steps.

Exam Information Curve.png
The maximization process, as the exam and IRT estimation evolve, for the task of generating abstracts for arXiv papers.

To expand our approach beyond Q&A applications, our future research will focus on domains such as summarization, translation, and sentiment analysis. We are also addressing the complex task of meta-evaluation, comparing and refining our evaluation methods to account for the multidimensional nature of LLM performance. Additionally, we will continuously update our methodologies to accommodate the rapid evolution of LLM technology, ensuring robust and comprehensive assessment of emerging models.

Acknowledgments: Laurent Callot

Research areas

Related content

IN, TS, Hyderabad
Welcome to the Worldwide Returns & ReCommerce team (WWR&R) at Amazon.com. WWR&R is an agile, innovative organization dedicated to ‘making zero happen’ to benefit our customers, our company, and the environment. Our goal is to achieve the three zeroes: zero cost of returns, zero waste, and zero defects. We do this by developing products and driving truly innovative operational excellence to help customers keep what they buy, recover returned and damaged product value, keep thousands of tons of waste from landfills, and create the best customer returns experience in the world. We have an eye to the future – we create long-term value at Amazon by focusing not just on the bottom line, but on the planet. We are building the most sustainable re-use channel we can by driving multiple aspects of the Circular Economy for Amazon – Returns & ReCommerce. Amazon WWR&R is comprised of business, product, operational, program, software engineering and data teams that manage the life of a returned or damaged product from a customer to the warehouse and on to its next best use. Our work is broad and deep: we train machine learning models to automate routing and find signals to optimize re-use; we invent new channels to give products a second life; we develop highly respected product support to help customers love what they buy; we pilot smarter product evaluations; we work from the customer backward to find ways to make the return experience remarkably delightful and easy; and we do it all while scrutinizing our business with laser focus. You will help create everything from customer-facing and vendor-facing websites to the internal software and tools behind the reverse-logistics process. You can develop scalable, high-availability solutions to solve complex and broad business problems. We are a group that has fun at work while driving incredible customer, business, and environmental impact. We are backed by a strong leadership group dedicated to operational excellence that empowers a reasonable work-life balance. As an established, experienced team, we offer the scope and support needed for substantial career growth. Amazon is earth’s most customer-centric company and through WWR&R, the earth is our customer too. Come join us and innovate with the Amazon Worldwide Returns & ReCommerce team!
US, MA, Westborough
Amazon is looking for talented Postdoctoral Scientists to join our Fulfillment Technology and Robotics team for a one-year, full-time research position. The Innovation Lab in BOS27 is a physical space in which new ideas can be explored, hands-on. The Lab provides easier access to tools and equipment our inventors need while also incubating critical technologies necessary for future robotic products. The Lab is intended to not only develop new technologies that can be used in future Fulfillment, Technology, and Robotics products but additionally promote deeper technical collaboration with universities from around the world. The Lab’s research efforts are focused on highly autonomous systems inclusive of robotic manipulation of packages and ASINs, multi-robot systems utilizing vertical space, Amazon integrated gantries, advancements in perception, and collaborative robotics. These five areas of research represent an impactful set of technical capabilities that when realized at a world class level will unlock our desire for a highly automated and adaptable fulfillment supply chain. As a Postdoctoral Scientist you will be developing a coordinated multi-agent system to achieve optimized trajectories under realistic constraints. The project will explore the utility of state-of-the-art methods to solve multi-agent, multi-objective optimization problems with stochastic time and location constraints. The project is motivated by a new technology being developed in the Innovation Lab to introduce efficiencies in the last-mile delivery systems. Key job responsibilities In this role you will: * Work closely with a senior science advisor, collaborate with other scientists and engineers, and be part of Amazon’s diverse global science community. * Publish your innovation in top-tier academic venues and hone your presentation skills. * Be inspired by challenges and opportunities to invent new techniques in your area(s) of expertise.
GB, MLN, Edinburgh
We’re looking for a Machine Learning Scientist in the Personalization team for our Edinburgh office experienced in generative AI and large models. You will be responsible for developing and disseminating customer-facing personalized recommendation models. This is a hands-on role with global impact working with a team of world-class engineers and scientists across the Edinburgh offices and wider organization. You will lead the design of machine learning models that scale to very large quantities of data, and serve high-scale low-latency recommendations to all customers worldwide. You will embody scientific rigor, designing and executing experiments to demonstrate the technical efficacy and business value of your methods. You will work alongside a science team to delight customers by aiding in recommendations relevancy, and raise the profile of Amazon as a global leader in machine learning and personalization. Successful candidates will have strong technical ability, focus on customers by applying a customer-first approach, excellent teamwork and communication skills, and a motivation to achieve results in a fast-paced environment. Our position offers exceptional opportunities for every candidate to grow their technical and non-technical skills. If you are selected, you have the opportunity to make a difference to our business by designing and building state of the art machine learning systems on big data, leveraging Amazon’s vast computing resources (AWS), working on exciting and challenging projects, and delivering meaningful results to customers world-wide. Key job responsibilities Develop machine learning algorithms for high-scale recommendations problems. Rapidly design, prototype and test many possible hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgement. Collaborate with software engineers to integrate successful experimental results into large-scale, highly complex Amazon production systems capable of handling 100,000s of transactions per second at low latency. Report results in a manner which is both statistically rigorous and compellingly relevant, exemplifying good scientific practice in a business environment.
US, CA, Palo Alto
Amazon’s Advertising Technology team builds the technology infrastructure and ad serving systems to manage billions of advertising queries every day. The result is better quality advertising for publishers and more relevant ads for customers. In this organization you’ll experience the benefits of working in a dynamic, entrepreneurial environment, while leveraging the resources of Amazon.com (AMZN), one of the world's leading companies. Amazon Publisher Services (APS) helps publishers of all sizes and on all channels better monetize their content through effective advertising. APS unites publishers with advertisers across devices and media channels. We work with Amazon teams across the globe to solve complex problems for our customers. The end results are Amazon products that let publishers focus on what they do best - publishing. The APS Publisher Products Engineering team is responsible for building cloud-based advertising technology services that help Web, Mobile, Streaming TV broadcasters and Audio publishers grow their business. The engineering team focuses on unlocking our ad tech on the most impactful Desktop, mobile and Connected TV devices in the home, bringing real-time capabilities to this medium for the first time. As a Data Scientist in our team, you will collaborate directly with developers and scientists to produce modeling solutions, you will partner with software developers and data engineers to build end-to-end data pipelines and production code, and you will have exposure to senior leadership as we communicate results and provide scientific guidance to the business. You will analyze large amounts of business data, automate and scale the analysis, and develop metrics (like ROAS, Share of Wallet) that will enable us to continually delight our customers worldwide. As a successful data scientist, you are an analytical problem solver who enjoys diving into data, is excited about investigations and algorithms, can multi-task, and can credibly interface between technical teams and business stakeholders. Your analytical abilities, business understanding, and technical aptitude will be used to identify specific and actionable opportunities to solve existing business problems and look around corners for future opportunities. Your expertise in synthesizing and communicating insights and recommendations to audiences of varying levels of technical sophistication will enable you to answer specific business questions and innovate for the future. Major responsibilities include: · Utilizing code (Apache, Spark, Python, R, Scala, etc.) for analyzing data and building statistical models to solve specific business problems. · Collaborate with product, BIEs, software developers, and business leaders to define product requirements and provide analytical support · Build customer-facing reporting to provide insights and metrics which track system performance · Communicating verbally and in writing to business customers and leadership team with various levels of technical knowledge, educating them about our systems, as well as sharing insights and recommendations
US, WA, Seattle
Amazon Advertising operates at the intersection of eCommerce and advertising, and is investing heavily in building a world-class advertising business. We are defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long-term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products to improve both shopper and advertiser experience. With a broad mandate to experiment and innovate, we grow at an unprecedented rate with a seemingly endless range of new opportunities. The Ad Response Prediction team in Sponsored Products organization build advanced deep-learning models, large-scale machine-learning pipelines, and real-time serving infra to match shoppers’ intent to relevant ads on all devices, for all contexts and in all marketplaces. Through precise estimation of shoppers’ interaction with ads and their long-term value, we aim to drive optimal ads allocation and pricing, and help to deliver a relevant, engaging and delightful ads experience to Amazon shoppers. As the business and the complexity of various new initiatives we take continues to grow, we are looking for talented Applied Scientists to join the team. Key job responsibilities As a Applied Scientist II, you will: * Conduct hands-on data analysis, build large-scale machine-learning models and pipelines * Work closely with software engineers on detailed requirements, technical designs and implementation of end-to-end solutions in production * Run regular A/B experiments, gather data, perform statistical analysis, and communicate the impact to senior management * Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving * Provide technical leadership, research new machine learning approaches to drive continued scientific innovation * Be a member of the Amazon-wide Machine Learning Community, participating in internal and external MeetUps, Hackathons and Conferences
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! In Prime Video READI, our mission is to automate infrastructure scaling and operational readiness. We are growing a team specialized in time series modeling, forecasting, and release safety. This team will invent and develop algorithms for forecasting multi-dimensional related time series. The team will develop forecasts on key business dimensions with optimization recommendations related to performance and efficiency opportunities across our global software environment. As a founding member of the core team, you will apply your deep coding, modeling and statistical knowledge to concrete problems that have broad cross-organizational, global, and technology impact. Your work will focus on retrieving, cleansing and preparing large scale datasets, 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 complete independence and are often assigned to focus on areas where the business and/or architectural strategy has not yet been defined. You must be equally comfortable digging in to business 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. 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 delivering for our customers, continually earning their trust, and thinking long term. You are empowered to bring new technologies to your solutions. If you crave a sense of ownership, this is the place to be.
US, WA, Bellevue
mmPROS Surface Research Science seeks an exceptional Applied Scientist with expertise in optimization and machine learning to optimize Amazon's middle mile transportation network, the backbone of its logistics operations. Amazon's middle mile transportation network utilizes a fleet of semi-trucks, trains, and airplanes to transport millions of packages and other freight between warehouses, vendor facilities, and customers, on time and at low cost. The Surface Research Science team delivers innovation, models, algorithms, and other scientific solutions to efficiently plan and operate the middle mile surface (truck and rail) transportation network. The team focuses on large-scale problems in vehicle route planning, capacity procurement, network design, forecasting, and equipment re-balancing. Your role will be to build innovative optimization and machine learning models to improve driver routing and procurement efficiency. Your models will impact business decisions worth billions of dollars and improve the delivery experience for millions of customers. You will operate as part of a team of innovative, experienced scientists working on optimization and machine learning. You will work in close collaboration with partners across product, engineering, business intelligence, and operations. Key job responsibilities - Design and develop optimization and machine learning models to inform our hardest planning decisions. - Implement models and algorithms in Amazon's production software. - Lead and partner with product, engineering, and operations teams to drive modeling and technical design for complex business problems. - Lead complex modeling and data analyses to aid management in making key business decisions and set new policies. - Write documentation for scientific and business audiences. About the team This role is part of mmPROS Surface Research Science. Our mission is to build the most efficient and optimal transportation network on the planet, using our science and technology as our biggest advantage. We leverage technologies in optimization, operations research, and machine learning to grow our businesses and solve Amazon's unique logistical challenges. Scientists in the team work in close collaboration with each other and with partners across product, software engineering, business intelligence, and operations. They regularly interact with software engineering teams and business leadership.
US, WA, Seattle
Success in any organization begins with its people and having a comprehensive understanding of our workforce and how we best utilize their unique skills and experience is paramount to our future success.. Come join the team that owns the technology behind AWS People Planning products, services, and metrics. We leverage technology to improve the experience of AWS Executives, HR/Recruiting/Finance leaders, and internal AWS planning partners. A Sr. Data Scientist in the AWS Workforce Planning team, will partner with Software Engineers, Data Engineers and other Scientists, TPMs, Product Managers and Senior Management to help create world-class solutions. We're looking for people who are passionate about innovating on behalf of customers, demonstrate a high degree of product ownership, and want to have fun while they make history. You will leverage your knowledge in machine learning, advanced analytics, metrics, reporting, and analytic tooling/languages to analyze and translate the data into meaningful insights. You will have end-to-end ownership of operational and technical aspects of the insights you are building for the business, and will play an integral role in strategic decision-making. Further, you will build solutions leveraging advanced analytics that enable stakeholders to manage the business and make effective decisions, partner with internal teams to identify process and system improvement opportunities. As a tech expert, you will be an advocate for compelling user experiences and will demonstrate the value of automation and data-driven planning tools in the People Experience and Technology space. Key job responsibilities * Engineering execution - drive crisp and timely execution of milestones, consider and advise on key design and technology trade-offs with engineering teams * Priority management - manage diverse requests and dependencies from teams * Process improvements – define, implement and continuously improve delivery and operational efficiency * Stakeholder management – interface with and influence your stakeholders, balancing business needs vs. technical constraints and driving clarity in ambiguous situations * Operational Excellence – monitor metrics and program health, anticipate and clear blockers, manage escalations To be successful on this journey, you love having high standards for yourself and everyone you work with, and always look for opportunities to make our services better.
US, WA, Seattle
Here at Amazon, we embrace our differences. We are committed to furthering our culture of diversity and inclusion of our teams within the organization. We’re working on the future. If you are seeking an iterative fast-paced environment where you can drive innovation, apply state-of-the-art technologies to solve extreme-scale real world delivery challenges, and provide visible benefit to end-users, this is your opportunity. Come work on the Amazon Prime Air team! We're looking for an outstanding Applied Scientist with either some background or strong interest in building simulation tools and algorithms for orchestration of a fleet of autonomous delivery drones. Managing a large number of concurrent autonomous drone flights that share airspace with other autonomous or manned aircrafts is a challenging problem. Be part of the team building simulation tools and algorithms to solve this at scale. This role will contribute to a portfolio of simulation tools managing concurrent airspace traffic for aviation systems. The ideal candidate is comfortable with a degree of risk taking and ambiguity and able to build consensus on the critical path. If you enjoy the process of solving real-world problems that, quite frankly, haven’t been solved at scale anywhere before, Prime Air could be the place for you. Along the way, we guarantee you’ll get opportunities to be a fearless disruptor, prolific innovator, and a reputed problem solver and directly impact Amazon’s customer’s worldwide. About the team Prime air has ambitious goals to offer its service to an increasing number of customers and enabling a large number of concurrent flights is central to achieving this. To this end, the air traffic management team is building algorithms, tools and services for orchestration of prime air's autonomous drone fleet.
CA, ON, Toronto
Amazon Games recherche un.e Chercheuse, Chercheur scientifique pour créer de nouvelles approches révolutionnaires en ML, RL et IA Générative qui raviront les joueuses et les joueurs. Dans ce rôle, vous collaborerez avec les Scientifiques en apprentissage automatique d'Amazon Games et Amazon Science pour imaginer et développer des outils, des processus et des fonctionnalités alimentés par l'IA générative à travers Amazon Games. Chez Amazon Games, notre ambition est de créer d’expériences inédites et audacieuses qui rassemblent et cultivent les communautés de joueurs et de joueuses. Notre équipe d'experts de l'industrie développe des jeux multijoueurs AAA et des propriétés intellectuelles originales, avec des équipes à Seattle, Orange County, San Diego, Montréal et Bucarest. À travers nos divisions - Studios, Publishing et Prime Gaming et en collaboration avec des partenaires externes, nous développons, publions et livrons des jeux et des expériences de contenu exceptionnelles pour les joueurs et joueuses. /// Amazon Games is seeking a highly effective Research Scientist to create new ground breaking ML, RL and Generative AI (Gen AI) approaches that delights player. In this role, you will collaborate with Amazon Science and Amazon Games Applied Scientists to research and develop generative AI-powered tools, pipelines and features across Amazon Games. At Amazon Games, our ambition is to create bold new experiences that foster community in and around our games. Our team of game industry veterans develops AAA multiplayer games and original IPs, with teams in Seattle, Orange County, San Diego, Montreal, and Bucharest. Amazon Games, through its Studios, Publishing, and Prime Gaming divisions collaborating with external partners, aims to develop, publish, and deliver compelling AAA games and content experiences for gamers to discover. Key job responsibilities Responsabilités - Rechercher, implémenter et produire des services d'IA/ML ambitieux et complexes pour Amazon Games. - Collaborer avec les équipes d'ingénieries, de conceptions et artistiques pour concevoir, développer et intégrer de nouveaux outils d'IA générative dans les flux de travail des équipes de développement. - Identifier et résoudre de manière proactive les problèmes qui affectent la qualité de vie des joueuses et les joueurs, des opérations et d’autres développeuses et développeurs. - Rester à jour et analyser les dernières avancées en technologie d'IA générative, et améliorer continuellement les fonctionnalités des produits lorsque des améliorations significatives en termes de coût, d'évolutivité, de qualité ou de fonctionnalité peuvent être réalisées. /// Responsibilities - Research, implement, and productionize ambitious and complex AI/ML services for Amazon Games. - Collaborate with game team engineers, designers and artists to design, develop, and integrate new generative AI tools into developer workflows. - Proactively identify and solve problems that affect the quality of life for players, operations, and other developers. - Stay up to date with and analyze the latest advancements in generative AI technology, and continuously improve product features where meaningful improvements in cost, scalability, quality, or functionality can be achieved. A day in the life Une journée type - Vous vous épanouissez dans un environnement collaboratif où vos décisions ont un impact et une influence significatifs. - Vous exprimer votre passion par la création d'expériences de jeu qui ravissent les joueurs et les joueuses. - Vous proposez d'excellents flux de travail, outils et innovations de jeu à vos collègues et aux équipes de développement et recherchez constamment l'amélioration. - Vous souhaitez faire partie de quelque chose d'excitant et unique dans l'écosystème du jeu. /// A day in the life - You thrive in a collaborative environment where your decisions have significant impact and influence. - You are passionate about building game experiences that delight players. - You deliver great workflows, tools, and game innovations to your fellow developers and constantly seek improvement. - You want to be part of something exciting and unique in the gaming ecosystem. About the team À propos de l'équipe L'équipe de recherche en IA d'Amazon Games Studio se concentre sur l'innovation en intelligence artificielle dans le domaine du jeu vidéo. Notre équipe hautement qualifiée et multidisciplinaire travaille sur l'apprentissage automatique, l'apprentissage par renforcement et l'IA générative pour réinventer le développement des jeux. Nous travaillons de près avec les équipes internes et nos studios partenaires pour donner vie à leur vision créative. Notre mission est d'utiliser l'IA de manière responsable pour transformer l'expérience de jeu, enrichir les récits, et fournir aux créateurs et créatrices des outils pratiques pour optimiser leurs chaînes de production. /// About the team The Amazon Games Studio AI Research team focuses on artificial intelligence innovation in gaming. Our highly skilled, multi-discipline team works across Machine Learning, Reinforcement Learning, and Generative AI to reimagine game development. We work closely with first-party game developers and partner studios to bring creative visions to life. Our mission is to use AI responsibly to transform gameplay experiences, enrich narratives, and provide creators with practical tools to optimize their production pipelines.