Social
Conversational AI

A quick guide to Amazon's 40+ papers at EMNLP 2023

Research on natural-language understanding seeks to harness the power of large language models, while query reformulation and text summarization emerge as topics of particular interest.

By Staff writer
December 6, 2023
6 min read
Share

Natural-language understanding (NLU) has long been a central focus of the papers that Amazon researchers publish at the Conference on Empirical Methods in Natural-Language Processing (EMNLP), but at this year's conference, which starts today, Amazon's NLU research shows a particular interest in harnessing the power of large language models (LLMs). Question answering also remains an active research topic, while query reformulation and text summarization emerge as new areas of concentration.

Automatic speech recognition

AdaBERT-CTC: Leveraging BERT-CTC for text-only domain adaptation in ASR
Tyler Vuong, Karel Mundnich, Dhanush Bekal, Veera Raghavendra Elluru, Srikanth Ronanki, Sravan Bodapati

Continual learning

Coordinated replay sample selection for continual federated learning
Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta 

Data extraction

InsightNet: Structured insight mining from customer feedback
Sandeep Mukku, Manan Soni, Chetan Aggarwal, Jitenkumar Rana, Promod Yenigalla, Rashmi Patange, Shyam Mohan

Knowledge-selective pretraining for attribute value extraction
Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chenwei Zhang, Bing Yin, William Wang, Xiaodan Zhu

Data selection

Influence scores at scale for efficient language data sampling
Nikhil Anand, Joshua Tan, Maria Minakova

Document understanding

A multi-modal multilingual benchmark for document image classification
Yoshinari Fujinuma, Siddharth Varia, Nishant Sankaran, Bonan Min, Srikar Appalaraju, Yogarshi Vyas

Semantic matching for text classification with complex class descriptions
Brian de Silva, Kuan-Wen Huang, Gwang Lee, Karen Hovsepian, Yan Xu, Mingwei Shen

Embodied task completion

Multimodal embodied plan prediction augmented with synthetic embodied dialogue
Aishwarya Padmakumar, Mert Inan, Spandana Gella, Patrick Lange, Dilek Hakkani-Tür

Entity linking

MReFinED: An efficient end-to-end multilingual entity linking system
Peerat Limkonchotiwat, Weiwei Cheng, Christos Christodoulopoulos, Amir Saffari, Jens Lehmann

Few-shot learning

Automated few-shot classification with instruction-finetuned language models
Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Wilson

AuT-Few.png
A schematic view of the Aut-Few prompt automation method. From "Automated few-shot classification with instruction-finetuned language models".

Information retrieval

Deep metric learning to hierarchically rank—An application in product retrieval
Kee Kiat Koo, Ashutosh Joshi, Nishaanth Reddy, Ismail Tutar, Vaclav Petricek, Changhe Yuan, Karim Bouyarmane

KD-Boost: Boosting real-time semantic matching in e-commerce with knowledge distillation
Sanjay Agrawal, Vivek Sembium, Ankith M S

CESAR.png
The CESAR framework automatically merges compound tasks — such as, in this example, keyword-controlled generation and act-grounded generation. From "CESAR: Automatic induction of compositional instructions for multi-turn dialogs".

Multi-teacher distillation for multilingual spelling correction
Jingfen Zhang, Xuan Guo, Sravan Bodapati, Christopher Potts

Instruction tuning

CESAR: Automatic induction of compositional instructions for multi-turn dialogs
Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tür, Yang Liu, Mahdi Namazifar

LLM hallucination

INVITE: A testbed of automatically generated invalid questions to evaluate large language models for hallucinations
Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi

Machine learning

Efficient long-range transformers: You need to attend more, but not necessarily at every layer
Qingru Zhang, Dhananjay Ram, Cole Hawkins, Sheng Zha, Tuo Zhao

Natural-language processing

NameGuess: Column name expansion for tabular data
Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Shen Wang, Huzefa Rangwala, George Karypis

Natural-language understanding

Adversarial robustness for large-language NER models using disentanglement and word attributions
Xiaomeng Jin, Bhanu Vinzamuri, Sriram Venkatapathy, Heng Ji, Pradeep Natarajan

Measuring and mitigating dialog-to-API constraint violations of in-context learning
Shufan Wang, Sebastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang

Intent classification.png
Overview of the pretraining of an intent-aware encoder. Given an utterance, x1, from the pretraining corpus, Amazon researchers generate a pseudo intent name, y1pseudo, using labels from the intent-role-labeling (IRL) tagger. The model is then optimized by pulling the gold utterance x1gold, the gold intent y1, and the pseudo intent, y1pseudo, close to the input utterance, x1, in the embedding space. From "Pre-training intent-aware encoders for zero- and few-shot intent classification".

MultiCoNER v2: A large multilingual dataset for fine-grained and noisy named entity recognition
Besnik Fetahu, Zhiyu Chen, Sudipta Kar, Oleg Rokhlenko, Shervin Malmasi

Pre-training intent-aware encoders for zero- and few-shot intent classification
Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli

Personalization

Personalized dense retrieval on global index for voice-enabled conversational systems
Masha Belyi, Charlotte Dzialo, Chaitanya Dwivedi, Prajit Reddy Muppidi, Kanna Shimizu

Retrieve and copy: Scaling ASR personalization to large catalogs
Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal, Srikanth Ronanki, Sravan Bodapati

Query reformulation

CL-QR: Cross-lingual enhanced query reformulation for multi-lingual conversational AI agents
Zhongkai Sun, Zhengyang Zhao, Sixing Lu, Chengyuan Ma, Xiaohu Liu, Xing Fan, Wei (Sawyer) Shen, Chenlei (Edward) Guo

Graph meets LLM: A novel approach to collaborative filtering for robust conversational understanding
Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan

Improving contextual query rewrite for conversational AI agents through user-preference feedback learning
Zhongkai Sun, Yingxue Zhou, Jie Hao, Xing Fan, Yanbin Lu, Chengyuan Ma, Wei (Sawyer) Shen, Chenlei (Edward) Guo

Question-answer databases

Protege: Prompt-based diverse question generation from web articles
Vinayak Puranik, Anirban Majumder, Vineet Chaoji

QUADRo: Dataset and models for question-answer database retrieval
Stefano Campese, Ivano Lauriola, Alessandro Moschitti

Question answering

Strong and efficient baselines for open domain conversational question answering
Andrei C. Coman, Gianni Barlacchi, Adrià de Gispert

Tokenization consistency matters for generative models on extractive NLP tasks
Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Yang Wang, Zhiheng Huang

Too much of product information: Don’t worry, let’s look for evidence!
Aryan Jain, Jitenkumar Rana, Chetan Aggarwal

Reasoning

Plan, verify and switch: Integrated reasoning with diverse x-of-thoughts
Tengxiao Liu, Qipeng Guo, Yuqing Yang, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang 

XOT.png
An overview of the x-of-thought (XoT) problem-solving framework, which integrates chain-of-thought (CoT) and program-of-thought (PoT) methods with the researchers' novel equation-of-thought (EoT) approach. From "Plan, verify and switch: Integrated reasoning with diverse x-of-thoughts".

Responsible AI

Geographical erasure in language generation
Pola Schwöbel, Jacek Golebiowski, Michele Donini, Cédric Archambeau, Danish Pruthi

Speech translation

End-to-end single-channel speaker-turn aware conversational speech translation
Juan Pablo Zuluaga Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico

Text summarization

Enhancing abstractiveness of summarization models through calibrated distillation
Hwanjun Song, Igor Shalyminov, Hang Su, Siffi Singh, Kaisheng Yao, Saab Mansour

Generating summaries with controllable readability levels
Leonardo Ribeiro, Mohit Bansal, Markus Dreyer

Improving consistency for text summarization with energy functions
Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang

InstructPTS: Instruction-tuning LLMs for product title summarization
Besnik Fetahu, Zhiyu Chen, Oleg Rokhlenko, Shervin Malmasi

Multi document summarization evaluation in the presence of damaging content
Avshalom Manevich, David Carmel, Nachshon Cohen, Elad Kravi, Ori Shapira

Re-examining summarization evaluation across multiple quality criteria
Ori Ernst, Ori Shapira, Ido Dagan, Ran Levy

Topic modeling

DeTiME: Diffusion-enhanced topic modeling using encoder-decoder based LLM
Weijie Xu, Wenxiang Hu, Fanyou Wu, Srinivasan Sengamedu, "SHS"

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Member of Technical Staff Intern (2026), Artificial General Intelligence (AGI)
US, CA, San Francisco
Amazon has launched a new research lab in San Francisco to develop foundational capabilities for useful AI agents. We’re enabling practical AI to make our customers more productive, empowered, and fulfilled. In particular, our work combines large language models (LLMs) with reinforcement learning (RL) to solve reasoning, planning, and world modeling in both virtual and physical environments. Our research builds on that of Amazon’s broader AGI organization, which recently introduced Amazon Nova, a new generation of state-of-the-art foundation models (FMs). Our lab is a small, talent-dense team with the resources and scale of Amazon. Each team in the lab has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research. We’re entering an exciting new era where agents can redefine what AI makes possible. We’d love for you to join our lab and build it from the ground up! Key job responsibilities You will contribute directly to AI agent development in a research engineering role: running experiments, building tools to accelerate scientific workflows, and scaling up AI systems. Key responsibilities include: * Design, maintain, and enhance tools and workflows that support cutting-edge research * Adapt quickly to evolving research priorities and team needs * Stay informed on the latest advancements in large language models and related research * Collaborate closely with researchers to develop new techniques and tools around emerging agent capabilities * Drive project execution, including scoping, prioritization, timeline management, and stakeholder communication * Thrive in a fast-paced, iterative environment, delivering high-quality software on tight schedules * Apply strong software engineering fundamentals to produce clean, reliable, and maintainable code About the team The Amazon AGI SF Lab is focused on developing new foundational capabilities for enabling useful AI agents that can take actions in the digital and physical worlds. In other words, we’re enabling practical AI that can actually do things for us and make our customers more productive, empowered, and fulfilled. The lab is designed to empower AI researchers and engineers to make major breakthroughs with speed and focus toward this goal. Our philosophy combines the agility of a startup with the resources of Amazon. By keeping the team lean, we’re able to maximize the amount of compute per person. Each team in the lab has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research.
Applied Scientist, Prime Video - Generative AI
US, CA, Sunnyvale
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 subscriptions such as Apple TV+, HBO Max, Peacock, 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 team member, 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! Key job responsibilities As an Applied Scientist at Prime Video, you will have end-to-end ownership of the product, related research and experimentation, applying advanced machine learning techniques in computer vision (CV), Generative AI, multimedia understanding and so on. You’ll work on diverse projects that enhance Prime Video’s content localization, image/video understanding, and content personalization, driving impactful innovations for our global audience. Other responsibilities include: - Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia - Innovate in advanced diffusion and flow-based methods (e.g., inverse flow matching, parameter efficient training, guided sampling, test-time adaptation) to improve efficiency, controllability, and scalability. - Advance visual grounding, depth and 3D estimation, segmentation, and matting for integration into pre-visualization, compositing, VFX, and post-production pipelines. - Design multimodal GenAI workflows including visual-language model tooling, structured prompt orchestration, agentic pipelines. A day in the life Prime Video is pioneering the use of Generative AI to empower the next generation of creatives. Our mission is to make world-class media creation accessible, scalable, and efficient. We are seeking an Applied Scientist to advance the state of the art in Generative AI and to deliver these innovations as production-ready systems at Amazon scale. Your work will give creators unprecedented freedom and control while driving new efficiencies across Prime Video’s global content and marketing pipelines. This is a newly formed team within Prime Video Science!
Applied Scientist, Prime Video - Generative AI
US, CA, Sunnyvale
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 subscriptions such as Apple TV+, HBO Max, Peacock, 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 team member, 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! Key job responsibilities As an Applied Scientist at Prime Video, you will have end-to-end ownership of the product, related research and experimentation, applying advanced machine learning techniques in computer vision (CV), Generative AI, multimedia understanding and so on. You’ll work on diverse projects that enhance Prime Video’s content localization, image/video understanding, and content personalization, driving impactful innovations for our global audience. Other responsibilities include: - Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia - Innovate in advanced diffusion and flow-based methods (e.g., inverse flow matching, parameter efficient training, guided sampling, test-time adaptation) to improve efficiency, controllability, and scalability. - Advance visual grounding, depth and 3D estimation, segmentation, and matting for integration into pre-visualization, compositing, VFX, and post-production pipelines. - Design multimodal GenAI workflows including visual-language model tooling, structured prompt orchestration, agentic pipelines. A day in the life Prime Video is pioneering the use of Generative AI to empower the next generation of creatives. Our mission is to make world-class media creation accessible, scalable, and efficient. We are seeking an Applied Scientist to advance the state of the art in Generative AI and to deliver these innovations as production-ready systems at Amazon scale. Your work will give creators unprecedented freedom and control while driving new efficiencies across Prime Video’s global content and marketing pipelines. This is a newly formed team within Prime Video Science!
Applied Scientist, Artificial General Intelligence - Data Services
US, MA, Boston
AI is the most transformational technology of our time, capable of tackling some of humanity’s most challenging problems. That is why Amazon is investing in generative AI (GenAI) and the responsible development and deployment of large language models (LLMs) across all of our businesses. Come build the future of human-technology interaction with us. We are looking for an Applied Scientist with strong technical skills which includes coding and natural language processing experience in dataset construction, training and evaluating models, and automatic processing of large datasets. You will play a critical role in driving innovation and advancing the state-of-the-art in natural language processing and machine learning. You will work closely with cross-functional teams, including product managers, language engineers, and other scientists. Key job responsibilities Specifically, the Applied Scientist will: • Ensure quality of speech/language/other data throughout all stages of acquisition and processing, including data sourcing/collection, ground truth generation, normalization, transformation, cross-lingual alignment/mapping, etc. • Clean, analyze and select speech/language/other data to achieve goals • Build and test models that elevate the customer experience • Collaborate with colleagues from science, engineering and business backgrounds • Present proposals and results in a clear manner backed by data and coupled with actionable conclusions • Work with engineers to develop efficient data querying infrastructure for both offline and online use cases
Member of Technical Staff, Artificial General Intelligence
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
Senior Applied Scientist, Artificial General Intelligence - Data Services
US, MA, Boston
AI is the most transformational technology of our time, capable of tackling some of humanity’s most challenging problems. That is why Amazon is investing in generative AI (GenAI) and the responsible development and deployment of large language models (LLMs) across all of our businesses. Come build the future of human-technology interaction with us. We are looking for an Applied Scientist with strong technical skills which includes coding and natural language processing experience in dataset construction, training and evaluating models, and automatic processing of large datasets. You will play a critical role in driving innovation and advancing the state-of-the-art in natural language processing and machine learning. You will work closely with cross-functional teams, including product managers, language engineers, and other scientists. Key job responsibilities Specifically, the Applied Scientist will: • Ensure quality of speech/language/other data throughout all stages of acquisition and processing, including data sourcing/collection, ground truth generation, normalization, transformation, cross-lingual alignment/mapping, etc. • Clean, analyze and select speech/language/other data to achieve goals • Build and test models that elevate the customer experience • Collaborate with colleagues from science, engineering and business backgrounds • Present proposals and results in a clear manner backed by data and coupled with actionable conclusions • Work with engineers to develop efficient data querying infrastructure for both offline and online use cases
Principal Applied Scientist, Artificial General Intelligence
US, CA, Sunnyvale
As a Principal Scientist in the Artificial General Intelligence (AGI) organization, you are a trusted part of the technical leadership. You bring business and industry context to science and technology decisions. You set the standard for scientific excellence and make decisions that affect the way we build and integrate algorithms. You solicit differing views across the organization and are willing to change your mind as you learn more. Your artifacts are exemplary and often used as reference across organization. You are a hands-on scientific leader. Your solutions are exemplary in terms of algorithm design, clarity, model structure, efficiency, and extensibility. You tackle intrinsically hard problems, acquiring expertise as needed. You decompose complex problems into straightforward solutions. You amplify your impact by leading scientific reviews within your organization or at your location. You scrutinize and review experimental design, modeling, verification and other research procedures. You probe assumptions, illuminate pitfalls, and foster shared understanding. You align teams toward coherent strategies. You educate, keeping the scientific community up to date on advanced techniques, state of the art approaches, the latest technologies, and trends. You help managers guide the career growth of other scientists by mentoring and play a significant role in hiring and developing scientists and leads. You will play a critical role in driving the development of Generative AI (GenAI) technologies that can handle Amazon-scale use cases and have a significant impact on our customers' experiences. Key job responsibilities You will be responsible for defining key research directions, adopting or inventing new machine learning techniques, conducting rigorous experiments, publishing results, and ensuring that research is translated into practice. You will develop long-term strategies, persuade teams to adopt those strategies, propose goals and deliver on them. You will also participate in organizational planning, hiring, mentorship and leadership development. You will be technically exceptional with a passion for building scalable science and engineering solutions. You will serve as a key scientific resource in full-cycle development (conception, design, implementation, testing to documentation, delivery, and maintenance).
Sr. Applied Scientist, People eXperience Technology Central Science (PXTCS)
US, NY, New York
Do you want to leverage your expertise in translating innovative science into impactful products to improve the lives and work of over a million people worldwide? If so, People eXperience Technology Central Science (PXTCS) would love to discuss how you can make that a reality. PXTCS is an interdisciplinary team that uses economics, behavioral science, statistics, and machine learning to identify products, mechanisms, and process improvements that enhance Amazonians' well-being and their ability to deliver value for Amazon's customers. We collaborate with HR teams across Amazon to make Amazon PXT the most scientific human resources organization in the world. In this role, you will spearhead science design and technical implementation innovations across our predictive modeling and forecasting work-streams. You'll enhance existing models and create new ones, empowering leaders throughout Amazon to make data-driven business decisions. You'll collaborate with scientists and engineers to deliver solutions while working closely with business stakeholders to address their specific needs. Your work will span various business domains (corporate, operations, safety) and analysis levels (individual, group, organizational), utilizing a range of modeling approaches (linear, tree-based, deep neural networks, and LLM-based). You'll develop end-to-end ML solutions from problem formulation to deployment, maintaining high scientific standards and technical excellence throughout the process. As a Sr. Applied Scientist, you'll also contribute to the team's science strategy, keeping pace with emerging AI/ML trends. You'll mentor junior scientists, fostering their growth by identifying high-impact opportunities. Your guidance will span different analysis levels and modeling approaches, enabling stakeholders to make informed, strategic decisions. If you excel at building advanced scientific solutions and are passionate about developing technologies that drive organizational change in the AI era, join us as we work hard, have fun, and make history.
Sr. Applied Scientist, Prime Video - Generative AI
US, CA, Sunnyvale
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 subscriptions such as Apple TV+, HBO Max, Peacock, 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 team member, 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! Key job responsibilities As an Applied Scientist at Prime Video, you will have end-to-end ownership of the product, related research and experimentation, applying advanced machine learning techniques in computer vision (CV), Generative AI, multimedia understanding and so on. You’ll work on diverse projects that enhance Prime Video’s content localization, image/video understanding, and content personalization, driving impactful innovations for our global audience. Other responsibilities include: - Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia - Innovate in advanced diffusion and flow-based methods (e.g., inverse flow matching, parameter efficient training, guided sampling, test-time adaptation) to improve efficiency, controllability, and scalability. - Advance visual grounding, depth and 3D estimation, segmentation, and matting for integration into pre-visualization, compositing, VFX, and post-production pipelines. - Design multimodal GenAI workflows including visual-language model tooling, structured prompt orchestration, agentic pipelines. A day in the life Prime Video is pioneering the use of Generative AI to empower the next generation of creatives. Our mission is to make world-class media creation accessible, scalable, and efficient. We are seeking an Applied Scientist to advance the state of the art in Generative AI and to deliver these innovations as production-ready systems at Amazon scale. Your work will give creators unprecedented freedom and control while driving new efficiencies across Prime Video’s global content and marketing pipelines. This is a newly formed team within Prime Video Science!
Applied Scientist, Catalog AI, Amazon Selection and Catalog Systems
US, WA, Seattle
Are you fascinated by the power of Large Language Models (LLM) and applying Generative AI to solve complex challenges within one of Amazon's most significant businesses? Amazon Selection and Catalog Systems (ASCS) builds the systems that host and run the world's largest e-Commerce products catalog, it powers the online buying experience for customers worldwide so they can find, discover and buy anything they want. Amazon's customers rely on the completeness, consistency and correctness of Amazon's product data to make well-informed purchase decisions. We develop LLM applications that make Catalog the best-in-class source of product information for all products worldwide. This problem is challenging due to sheer scale (billions of products in the catalog), diversity (products ranging from electronics to groceries) and multitude of input sources (millions of sellers contributing product data with different quality). We are seeking a passionate, talented, and inventive individual to join the Catalog AI team and help build industry-leading technologies that customers will love. You will apply machine learning and large language model techniques, such as fine-tuning, reinforcement learning, and prompt optimization, to solve real customer problems. You will work closely with scientists and engineers to experiment with new methods, run large-scale evaluations, and bring research ideas into production. Key job responsibilities * Design and implement LLM-based solutions to improve catalog data quality and completeness * Conduct experiments and A/B tests to validate model improvements and measure business impact * Optimize large language models for quality and cost on catalog-specific tasks * Collaborate with engineering teams to deploy models at scale serving billions of products
See more jobs
View from space of a connected network around planet Earth representing the Internet of Things.
Get more from Amazon Science
Subscribe to our monthly newsletter

Amazon.com | Conditions of Use | Privacy | © 1996-2025 Amazon.com, Inc. or its affiliates

Social