Social
Conversational AI

A quick guide to Amazon's 65-plus papers at this year's ACL

Familiar topics such as question answering and natural-language understanding remain well represented, but a new concentration on language modeling and multimodal models reflect the spread of generative AI.

By Staff writer
July 10, 2023
10 min read
Share

Between the main conference and the recently inaugurated ACL Proceedings, Amazon researchers have more than 65 papers at this year's meeting of the Association for Computational Linguistics (ACL).

Automatic speech recognition

Masked audio text encoders are effective multi-modal rescorers*
Jason Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati

Code generation

A static evaluation of code completion by large language models
Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng LI, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, Bing Xiang

Multitask pretraining with structured knowledge for text-to-SQL generation
Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma

Code switching

Code-switched text synthesis in unseen language pairs*
I-Hung Hsu, Avik Ray, Shubham Garg, Nanyun Peng, Jing Huang

Code-switched text synthesis.png
From "Code-switched text synthesis in unseen language pairs".

CoMix: Guide transformers to code-mix using POS structure and phonetics*
Gaurav Arora, Srujana Merugu, Vivek Sembium

Continual learning

Characterizing and measuring linguistic dataset drift
Tyler A. Chang, Kishaloy Halder, Neha Anna John, Yogarshi Vyas, Yassine Benajiba, Miguel Ballesteros, Dan Roth

Data-/table-to-text applications

An inner table retriever for robust table question answering
Weizhe Lin, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert, Gonzalo Iglesias

Few-shot data-to-text generation via unified representation and multi-source learning
Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, JIE MA, Patrick Ng, Zhiguo Wang, Bonan Min, William Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang

Improving cross-task generalization of unified table-to-text models with compositional task configurations*
Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Wang, Zhiheng Huang

LI-RAGE: Late interaction retrieval augmented generation with explicit signals for open-domain table question answering
Weizhe Lin, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert, Gonzalo Iglesias

Dialogue

Diable: Efficient dialogue state tracking as operations on tables*
Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Lluis Marquez

NatCS: Eliciting natural customer support dialogues
James Gung, Emily Moeng, Wesley Rose, Arshit Gupta, Yi Zhang, Saab Mansour

Schema-guided user satisfaction modeling for task-oriented dialogues
Yue Feng, Yunlong Jiao, Animesh Prasad, Nikolaos Aletras, Emine Yilmaz, Gabriella Kazai

Toward more accurate and generalizable evaluation metrics for task-oriented dialogs
Abi Komma, Nagesh Panyam, Timothy Leffel, Anuj Goyal, Angeliki Metallinou, Spyros Matsoukas, Aram Galstyan

Explainable AI

Efficient Shapley values estimation by amortization for text classification
Alan Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang

Efficient Shapley values.png
From "Efficient Shapley values estimation by amortization for text classification".

Few shot rationale generation using self-training with dual teachers*
Aditya Srikanth Veerubhotla, Lahari Poddar, Jun Yin, Gyuri Szarvas, Sharanya Eswaran

Information extraction

An AMR-based link prediction approach for document-level event argument extraction
Yuqing Yang, Qipeng Guo, Xiangkun Hu, Yue Zhang, Qipeng Guo, Zheng Zhang

AVEN-GR: Attribute value extraction and normalization using product graphs
Donato Crisostomi, Thomas Ricatte

Large scale generative multimodal attribute extraction for e-commerce attributes
Anant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni, Deepak Gupta

ParaAMR: A large-scale syntactically diverse paraphrase dataset by AMR back-translation
Kuan-Hao Huang, Varun Iyer, I-Hung Hsu, Anoop Kumar, Kai-Wei Chang, Aram Galstyan

ParaAMR.png
From "ParaAMR: A large-scale syntactically diverse paraphrase dataset by AMR back-translation".

Weakly supervised hierarchical multi-task classification of customer questions
Jitenkumar Rana, Promod Yenigalla, Chetan Aggarwal, Sandeep Mukku, Manan Soni, Rashmi Patange

WebIE: Faithful and robust information extraction on the web
Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni

Information retrieval

CUPID: Curriculum learning based real-time prediction using distillation
Arindam Bhattacharya, Ankith M S, Ankit Gandhi, Vijay Huddar, Atul Saroop, Rahul Bhagat

Direct fact retrieval from knowledge graphs without entity linking
Jinheon Baek, Alham Fikri Aji, Jens Lehmann, Sung Ju Hwang

Language modeling

Adaptation approaches for nearest neighbor language models*
Rishabh Bhardwaj, George Polovets, Monica Sunkara

CONTRACLM: Contrastive learning for causal language model
Nihal Jain, Dejiao Zhang, Wasi Ahmad, Zijian Wang, Feng Nan, Xiaopeng LI, Ming Tan, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Ramesh Nallapati, Bing Xiang

Controlled text generation with hidden representation transformations*
Vaibhav Kumar, Hana Koorehdavoudi, Masud Moshtaghi, Amita Misra, Ankit Chadha, Emilio Ferrara

KILM: Knowledge injection into encoder-decoder language models
Yan XU, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür

KILM.png
From "KILM: Knowledge injection into encoder-decoder language models".

ReAugKD: Retrieval-augmented knowledge distillation for pre-trained language models
Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen

Recipes for sequential pre-training of multilingual encoder and seq2seq models*
Saleh Soltan, Andy Rosenbaum, Tobias Falke, Qin Lu, Anna Rumshisky, Wael Hamza

Rethinking the role of scale for in-context learning: An interpretability-based case study at 66 billion scale
Hritik Bansal, Karthik Gopalakrishnan, Saket Dingliwal, Sravan Bodapati, Katrin Kirchhoff, Dan Roth

Machine learning

Mitigating the burden of redundant datasets via batch-wise unique samples and frequency-aware losses
Donato Crisostomi, Andrea Caciolai, Alessandro Pedrani, Alessandro Manzotti, Enrico Palumbo, Kay Rottmann, Davide Bernardi

Machine translation

RAMP: Retrieval and attribute-marking enhanced prompting for attribute-controlled translation
Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nădejde

Multimodal models

Benchmarking diverse-modal entity linking with generative models*
Sijia Wang, Alexander Li, Henry Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, JIE MA, William Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

Generate then select: Open-ended visual question answering guided by world knowledge*
Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henry Zhu, Yuhao Zhang, Alexander Hanbo Li, William Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

KG-FLIP: Knowledge-guided fashion-domain language-image pre-training for e-commerce
Qinjin Jia, Yang Liu, Shaoyuan Xu, Huidong Liu, Daoping Wu, Jinmiao Fu, Roland Vollgraf, Bryan Wang

Resolving ambiguities in text-to-image generative models
Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta

Translation-enhanced multilingual text-to-image generation
Yaoyiran Li, Ching-Yun (Frannie) Chang, Stephen Rawls, Ivan Vulić, Anna Korhonen

Unsupervised melody-to-lyric generation
Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Chenyang Tao, Gunnar Sigurdsson, Wenbo Zhao, Tagyoung Chung, Jing Huang, Violet Peng

Unsupervised melody-to-lyric.png
From "Unsupervised melody-to-lyric generation".

Natural-language processing

Multi-VALUE: A framework for cross-dialectal English NLP
Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang

vONTSS: vMF based semi-supervised neural topic modeling with optimal transport*
Weijie Xu, Xiaoyu Jiang, Srinivasan Sengamedu, "SHS", Francis Iannacci, Jinjin Zhao

Natural-language understanding

ECG-QALM: Entity-controlled synthetic text generation using contextual Q&A for NER*
Karan Aggarwal, Henry Jin, Aitzaz Ahmad

Entity contrastive learning in a large-scale virtual assistant system
Jonathan Rubin, Jason Crowley, George Leung, Morteza Ziyadi, Maria Minakova

EPIC: Multi-perspective annotation of a corpus of irony
Simona Frenda, Alessandro Pedrani, Valerio Basile, Soda Marem Lo, Alessandra Teresa Cignarella, Raffaella Panizzon, Cristina Marco, Bianca Scarlini, Viviana Patti, Cristina Bosco, Davide Bernardi

Measuring and mitigating local instability in deep neural networks*
Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan

Reducing cohort bias in natural language understanding systems with targeted self-training scheme
Thu Le, Gabriela Cortes Hernandez, Bei Chen, Melanie Bradford

Privacy

Controlling the extraction of memorized data from large language models via prompt-tuning
Mustafa Ozdayi, Charith Peris, Jack G. M. FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta

Query rewriting

Context-aware query rewriting for improving users’ search experience on e-commerce websites
Simiao Zuo, Qingyu Yin, Haoming Jiang, Shaohui Xi, Bing Yin, Chao Zhang, Tuo Zhao

Unified contextual query rewriting
Yingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Vasudevan, Kellen Gillespie, Zeynab Raeesy, Sawyer Shen, Edward Guo, Gokhan Tur

Question answering

Accurate training of web-based question answering systems with feedback from ranked users
Liang Wang, Ivano Lauriola, Alessandro Moschitti

Context-aware transformer pre-training for answer sentence selection
Luca Di Liello, Siddhant Garg, Alessandro Moschitti

Cross-Lingual Knowledge Distillation for answer sentence selection in low-resource languages*
Shivanshu Gupta, Yoshitomo Matsubara, Ankit Chadha, Alessandro Moschitti

Exploiting abstract meaning representation for open-domain question answering*
Cunxiang Wang, Zhikun Xu, Qipeng Guo, Xiangkun Hu, Xuefeng Bai, Zheng Zhang, Yue Zhang

Exploiting abstract meaning representation.png
From "Exploiting abstract meaning representation for open-domain question answering".

Hybrid hierarchical retrieval for open-domain question answering*
Manoj Ghuhan Arivazhagan, Lan Liu, Peng Qi, Xinchi Chen, William Wang, Zhiheng Huang

Learning answer generation using supervision from automatic question answering evaluators
Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti

RobustQA: Benchmarking the robustness of domain adaptation for open-domain question answering*
Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Wang, Zhiheng Huang, Bing Xiang, Dan Roth

Reasoning

FolkScope: Intention knowledge graph construction for e-commerce commonsense discovery*
Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

SCOTT: Self-consistent chain-of-thought distillation
Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren

Self-learning

Constrained policy optimization for controlled self-learning in conversational AI systems
Mohammad Kachuee, Sungjin Lee

Scalable and safe remediation of defective actions in self-learning conversational systems
Sarthak Ahuja, Mohammad Kachuee, Fateme Sheikholeslami, Weiqing Liu, Jae Do

Semantic parsing

An empirical analysis of leveraging knowledge for low-resource task-oriented semantic parsing*
Mayank Kulkarni, Aoxiao Zhong, Nicolas Guenon Des Mesnards, Sahar Movaghati, Mukund Harakere, He Xie, Jianhua Lu

XSEMPLR: Cross-lingual semantic parsing in multiple natural languages and meaning representations
Yusen Zhang, Jun Wang, Zhiguo Wang, Rui Zhang

XSemPLR.png
From "XSEMPLR: Cross-lingual semantic parsing in multiple natural languages and meaning representations".

Spoken-language understanding

Regression-free model updates for spoken language understanding
Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi

Sharing encoder representations across languages, domains and tasks in large-scale spoken language understanding
Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Satya Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev, Mariusz Momotko, Denis Romasanta Rodriguez, Austin Doolittle, Kartik Balasubramaniam, Wael Hamza, Fabian Triefenbach, Patrick Lehnen

Toxic-language classification

QCon at SemEval-2023 Task 10: Data augmentation and model ensembling for detection of online sexism
Wes Feely, Prabhakar Gupta, Manas Mohanty, Tim Chon, Tuhin Kundu, Vijit Singh, Sandeep Atluri, Tanya Roosta, Viviane Ghaderi, Peter Schulam, Heba Elfardy

Towards building a robust toxicity predictor
Dmitriy Bespalov, Sourav Bhabesh, Yi Xiang, Yanjun (Jane) Qi

*Accepted to ACL Findings

Research areas
Tags
About the Author
Staff writer

Related content

  • ARA-Fall26-16x9.png
    Amazon Research Awards recipients announced
    Amazon Research Awards team
    May 27, 2026
    Awardees represent more than 49 universities in 11 countries. Recipients have access to Amazon public datasets, along with AWS AI/ML services and tools.
  • PortableReasoning-Hero-16x9.png
    Portable reasoning: Releasing text-bound intelligence into agentic interaction
    Meiqi Sun
    April 20, 2026
    Large language models today can solve algebra, pass academic benchmarks, and generate highly structured chain-of-thought explanations. In text-only settings, they often feel startlingly intelligent — methodical, articulate, even strategic. But place those models inside an interactive environment — ask them to click buttons, scroll pages, fill out forms, and submit answers — and their behavior changes. Their careful reasoning falters. They guess where they once deduced. They adhere to templates and produce limited procedural narration: stating what they see and what they will click next, without first forming a structured plan and acting in accordance with plan. It’s as if part of their intelligence has quietly gone offline the moment the cursor appears.
    Machine learning
  • Promptimus-02b-16x9.png
    Promptimus: Improving already good LLM prompts with zero manual engineering
    Zhengyuan Shen, Yunfei Bai, Sullam Jeoung, Shuai Wang
    May 14, 2026
    By focusing on specific failure points and suggesting targeted solutions, a new automated prompt-engineering framework improves prompt performance without compromising existing functionality.

Work with us

See more jobs See more jobs
Applied Scientist, Prime Video - Generative AI
US, NY, New York
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 • Build generative AI models that create production-ready content, including movie content, localized assets, and visual marketing materials used across Prime Video's global platform. • Drive end-to-end machine learning projects that have a high degree of ambiguity, scale, complexity. • Build machine learning models, perform proof-of-concept, experiment, optimize, and deploy your models. • Run experiments, gather data, and perform statistical analysis. • Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving. • Research new and innovative machine learning approaches. • Share knowledge and research outcomes via internal and external conferences and journal publications 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 II, IESP Digital Payments
BR, SP, Sao Paulo
Do you like working on projects that are highly visible and are tied closely to Amazon’s growth? Are you seeking an environment where you can drive innovation leveraging the scalability and innovation with Amazon's AWS cloud services? The Amazon IESP Digital Payments & Emerging Team is hiring Applied Scientists to work in our Machine Learning team in São Paulo, Brazil. The Payments team designs and builds scalable payment systems that power Amazon's checkout and financial services across emerging countries (Brazil, Mexico, Australia, Singapore, and more). We tackle complex challenges in payment orchestration, fraud detection, and regional payment method integration to drive conversion and deliver seamless experiences at scale. Key job responsibilities About you You want to make changes that help millions of customers. You don’t want to make something 10% better as a part of an enormous team. Rather, you want to innovate with a small community of passionate peers. You have experience in analytics, machine learning, LLMs and Agentic AI, and a desire to learn more about these subjects. You want a trusted role in strategy and product design. You put the customer first in your thinking. You have great problem solving skills. You research the latest data technologies and use them to help you innovate and keep costs low. You have great judgment and communication skills, and a history of delivering results. Your Responsibilities - Define and own complex machine learning solutions in the consumer space, including targeting, measurement, creative optimization, and multivariate testing. - Design, implement, and evolve Agentic AI systems that can autonomously perceive their environment, reason about context, and take actions across business workflows—while ensuring human-in-the-loop oversight for high-stakes decisions. - Influence the broader team's approach to integrating machine learning into business workflows. - Advise leadership, both tech and non-tech. - Support technical trade-offs between short-term needs and long-term goals.
Machine Learning Scientist / Applied Scientist, EU Prime and Marketing Analytics & Science (PRIMAS)
ES, M, Madrid
Are you interested in building the measurement foundation that proves whether targeted, cohort-based marketing actually changes customer behavior at Amazon scale? We are seeking an Applied Scientist to own measurement and experimentation for our Lifecycle Marketing Experimentation roadmap within the PRIMAS (Prime & Marketing Analytics and Science) team. In this role, you will design and execute rigorous experiments that measure the effectiveness of audience-based marketing campaigns across multiple channels, providing the evidence that guides marketing strategy and investment decisions. This is a high-impact role where you will build measurement frameworks from scratch, design experiments that isolate causal effects, and establish the experimental standards for lifecycle marketing across EU. You will work closely with business leaders and the senior science lead to answer critical questions: does targeting specific cohorts (Bargain hunters, Young adults) improve efficiency vs. broad campaigns? Which creative strategies drive behavior change? How should we optimize marketing spend across channels? Key job responsibilities Measurement & Experimentation Ownership: 1. Own measurement end-to-end for lifecycle marketing campaigns – design experiments (RCTs, geo-tests, audience holdouts) that measure campaign effectiveness across marketing channels 2. Build measurement frameworks and experimental best practices that work across different activation platforms and can scale to multiple campaigns 3. Establish experimental standards and tooling for lifecycle marketing, ensuring statistical rigor while balancing business constraints Causal Inference & Analysis: 1. Apply causal inference methods to measure incremental impact of marketing campaigns vs. counterfactual 2. Navigate measurement challenges across different platforms (Meta attribution, LiveRamp, clean rooms, onsite tracking) 3. Analyze experiment results and provide optimization recommendations based on statistical evidence 4. Establish guardrails and success criteria for campaign evaluation About the team The PRIMAS team, is part of a larger tech tech team called WIMSI (WW Integrated Marketing Systems and Intelligence). WIMSI core mission is to accelerate marketing technology capabilities that enable de-averaged customer experiences across the marketing funnel: awareness, consideration, and conversion.
Senior Data Scientist, Amazon Leo
US, WA, Bellevue
Amazon Leo is Amazon’s low Earth orbit satellite broadband network. Its mission is to deliver fast, reliable internet to customers and communities around the world, and we’ve designed the system with the capacity, flexibility, and performance to serve a wide range of customers, from individual households to schools, hospitals, businesses, government agencies, and other organizations operating in locations without reliable connectivity. Export Control Requirement: Due to applicable export control laws and regulations, candidates must be a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum. As a Senior Data Scientist (DS), you will drive the development and implementation of advanced analytics and machine learning solutions. You will work on critical initiatives including natural language processing for non-conformance analysis, statistical process controls (SPC) for test optimization, and equipment predictive maintenance models to enable manufacturing rate acceleration. Your work will directly influence Kuiper’s production manufacturing workflow. You are an analytical problem solver who enjoys diving into data from various businesses, is excited about investigations and algorithms, can multi-task, and can credibly interface between scientists, engineers, and business stakeholders. 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. Key job responsibilities Lead the design and implementation of ML/LLM solutions to analyze manufacturing data and identify failure patterns and operational risks Design predictive models for statistical process control and equipment maintenance optimization Build production-ready ML pipelines leveraging AWS services (e.g., SageMaker, Bedrock, AWS Glue) Formalize assumptions about how models are expected to behave, creating definitions of outliers, developing methods to systematically identify these outliers, and explaining why they are reasonable or identifying fixes for them Develop and test model enhancements, running computational experiments, and fine-tuning model parameters for new models Collaborate with engineering teams to translate complex manufacturing challenges into data-driven solutions Drive consensus on metrics and analysis approaches to support business strategy Write documents and create compelling visualizations and presentations to communicate insights to stakeholders Mentor team members and drive data science best practices across the organization About the team Established in 2023 as ProdOps was preparing to transition from development into full-rate production, OCC was purpose-built to ensure that as manufacturing scaled, the most critical problems would be identified, solved, and prevented from recurring through a single integrated operating system. OCC focuses on the most critical problems for ProdOps at each phase of production. The team operates as a closed-loop flywheel where each rotation identifies value, solves problems, implements change, and generates new data that feeds the next cycle. Every rotation compounds returns.
Applied Scientist - Reinforcement learning, OMHS SCS
US, MA, N.reading
As an Applied Scientist on the Science SW team, you will collaborate closely with other scientists and engineers to bring Reinforcement Learning (RL) research to production. This role combines the scientific application of ML, and specifically RL and sequential decision making, with software development engineering and a strong product focus. It will be your job to design, implement, and deploy novel RL agents, reward models, and control policies in both prototype and production environments, and to prove their impact in high-fidelity simulation before scaling them across the fleet. Key job responsibilities • Own the research and development of reinforcement learning and sequential decision making solutions spanning deep RL, policy optimization, offline/batch RL, contextual bandits, and multi-agent RL for real-time MHE control and building-wide optimization in a production environment. • Formulate fulfillment operations problems (throughput optimization, flow, merge, and congestion control) as sequential decision-making problems, and design multi-objective reward functions that balance competing operational objectives. • Build and leverage high-fidelity simulation environments for safe offline training, policy validation, and sim-to-real transfer before fleet-scale deployment. • Collaborate across multiple science and engineering teams to integrate RL policies into real-time production and control systems. 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.
Sr. Applied Scientist, Prime Video - Personalization and Discovery Science
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 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! We are looking for a self-motivated, passionate and resourceful Applied Scientist to bring diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. You will spend your time as a hands-on machine learning practitioner and a research leader. You will play a key role on the team, building and guiding machine learning models from the ground up. At the end of the day, you will have the reward of seeing your contributions benefit millions of Amazon.com customers worldwide. Key job responsibilities - Develop AI solutions for various Prime Video Search systems using Deep learning, GenAI, Reinforcement Learning, and optimization methods; - Work closely with engineers and product managers to design, implement and launch AI solutions end-to-end; - Design and conduct offline and online (A/B) experiments to evaluate proposed solutions based on in-depth data analyses; - Effectively communicate technical and non-technical ideas with teammates and stakeholders; - Stay up-to-date with advancements and the latest modeling techniques in the field; - Publish your research findings in top conferences and journals. About the team Prime Video Search Science team owns science solution to power search experience on various devices, from sourcing, relevance, ranking, to name a few. We work closely with the engineering teams to launch our solutions in production.
Applied Scientist, Fauna
US, NY, New York
We are seeking an Applied Scientist to lead the development of evaluation frameworks and data collection protocols for robotic capabilities. In this role, you will focus on designing how we measure, stress-test, and improve robot behavior across a wide range of real-world tasks. Your work will play a critical role in shaping how policies are validated and how high-quality datasets are generated to accelerate system performance. You will operate at the intersection of robotics, machine learning, and human-in-the-loop systems, building the infrastructure and methodologies that connect teleoperation, evaluation, and learning. This includes developing evaluation policies, defining task structures, and contributing to operator-facing interfaces that enable scalable and reliable data collection. The ideal candidate is highly experimental, systems-oriented, and comfortable working across software, robotics, and data pipelines, with a strong focus on turning ambiguous capability goals into measurable and actionable evaluation systems. Key job responsibilities - Design and implement evaluation frameworks to measure robot capabilities across structured tasks, edge cases, and real-world scenarios - Develop task definitions, success criteria, and benchmarking methodologies that enable consistent and reproducible evaluation of policies - Create and refine data collection protocols that generate high-quality, task-relevant datasets aligned with model development needs - Build and iterate on teleoperation workflows and operator interfaces to support efficient, reliable, and scalable data collection - Analyze evaluation results and collected data to identify performance gaps, failure modes, and opportunities for targeted data collection - Collaborate with engineering teams to integrate evaluation tooling, logging systems, and data pipelines into the broader robotics stack - Stay current with advances in robotics, evaluation methodologies, and human-in-the-loop learning to continuously improve internal approaches - Lead technical projects from conception through production deployment - Mentor junior scientists and engineers
Research Scientist II, Last Mile Science
IN, KA, Bangalore
Are you passionate about solving complex logistics challenges? Our Analytics team is at the forefront of enhancing delivery experiences through data-driven solutions and innovative technology. As a Research Scientist, you will join a team dedicated to optimizing our delivery network, ensuring reliable and efficient service to our customers. We are seeking an enthusiastic, customer-centric professional with strong analytical capabilities to drive impactful projects, implement advanced solutions, and develop scalable processes. In this role, you will have immediate ownership of business-critical challenges and the opportunity to make strategic, data-driven decisions that shape the future of our delivery operations. Your work will directly influence customer experience and operational excellence. The ideal candidate will possess both research science capabilities and program management skills, thriving in an environment that requires independent decision-making and comfort with ambiguity. This role offers the opportunity to make a significant impact on our advanced logistics network while working with pioneering technology and data science applications. Basic qualifications • 3+ years of building machine learning models for business application experience • Knowledge of programming languages such as C/C++, Python, Java or Perl • Experience programming in Java, C++, Python or related language • Experience with neural deep learning methods and machine learning Preferred qualifications: • PhD in engineering, technology, computer science, machine learning, robotics, operations research, statistics, mathematics or equivalent quantitative field • 3+ years of extensive relevant research experience • Deep expertise in Machine Learning • Proficiency in programming • Core competency in mathematics and statistics • Track record of successful projects in algorithm design and product development • Publications at peer-reviewed conferences or journals • Strategic thinker with good execution skills • Exhibits excellent business judgment • Effective verbal and written communication skills • Experience working with real-world data sets and building scalable models from big data • Experience with modern modeling tools and frameworks such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow • Experience with large scale distributed systems
Sr. Applied Scientist, Foundation Model Build, WW Sustainability
US, WA, Seattle
Build AI systems that help Amazon make better sustainability decisions at global scale. Our research questions require more than applying an existing model: they require new scientific methods, trustworthy data foundations, and a path from research hypothesis to production deployment. Sustainability Science and Innovation (SSI) is Amazon's applied research hub for environmental impact. We bring together applied scientists, environmental scientists, economists, and engineers to develop and scale solutions across carbon, water, waste, climate risk, and responsible supply chains—from early hypothesis to production deployment at Amazon scale. SSI is seeking a Senior Applied Scientist to own a research agenda at the intersection of artificial intelligence, data, and sustainability. The role will define the science roadmap, formulate and test hypotheses, establish evaluation standards, and lead solutions from early experimentation through production deployment. Working closely with economists, environmental scientists, engineers, and product leaders, the Senior Applied Scientist will determine which scientific and technical approaches can produce decision-ready results at Amazon scale. The work may include large language models, multimodal models, retrieval-augmented generation, foundation-model adaptation, and other modern machine-learning methods, selected according to the scientific problem rather than applied as ends in themselves. The role will also define how strategic models and datasets are discovered, evaluated, ingested, harmonized, governed, and maintained, because trustworthy AI depends on traceable evidence, stable data contracts, and reproducible evaluation. Applications may include product-level carbon estimation, climate-risk monitoring, and responsible-supply-chain assessment. This role is distinctive because Amazon’s operational scale creates scientific problems that few organizations can study, with unique access to global-scale sustainability data. You'll leverage this unique access to establish scientific methods, governance models, and evaluation standards that can scale across multiple programs. This role shapes not just what problems we solve, but how we solve them rigorously setting a template for AI-driven sustainability science across Amazon's global operations. Candidates do not need prior expertise in sustainability or climate science. The role requires a hands-on scientific leader who can develop rigorous AI and machine-learning methods, work effectively across disciplines, and translate uncertain research questions into measurable, production-ready solutions. Key job responsibilities • Own the research agenda and multi-year science roadmap for AI-enabled sustainability solutions. • Develop and evaluate modern AI and machine-learning methods, including foundation models, multimodal models, retrieval-augmented generation, and model adaptation. • Establish ex ante evaluation criteria, benchmarks, and launch thresholds that distinguish promising prototypes from production-ready methods. • Lead the full scientific lifecycle, from problem formulation and experimentation through production deployment and post-launch measurement. • Define the architecture and governance required to make strategic models and datasets discoverable, traceable, reproducible, and reusable. • Influence senior science, engineering, product, and sustainability stakeholders across organizational boundaries. • Mentor scientists and raise the scientific standard through technical reviews, publications, and reusable methods. About the team Diverse Experiences: World Wide Sustainability values diverse experiences. Even if you do not meet all of the qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn’t followed a traditional path, or includes alternative experiences, don’t let it stop you from applying. Inclusive Team Culture: 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 (inclusive diversity) 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 flexible work hours and arrangements are part of our culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve.
Applied Scientist (2026-27 Campus, International Technology Team), Beijing
CN, 11, Beijing
北京职位 - 如果希望在北京工作，请投递本职位。 毕业时间：2026年10月 - 2027年9月之间毕业的应届毕业生 · 投递须知： 1 填写简历申请时，请把必填和非必填项都填写完整。提交简历之后就无法修改了哦！ 2 学校的英文全称请准确填写。中英文对应表，请点击链接查看 https://docs.qq.com/sheet/DVmdaa1BCV0RBbnlR?tab=BB08J2 3 简历不限中英文。 如果您正在攻读计算机，AI，ML等相关专业的博士或硕士研究生，而且对应用科学家的工作感兴趣。如果您也喜爱深入研究棘手的技术问题并提出解决方案，用成功的产品显著地改善人们的生活。 那么，我们诚挚邀请您加入亚马逊的International Technology搜索团队改善Amazon的产品和服务。我们的目标是帮助亚马逊的客户找到他们所需的产品，并发现他们感兴趣的新产品。这会是一份收获满满的工作。您每天的工作都与全球数百万亚马逊客户的体验紧密相关。您将提出创新，基于TB级别的产品和流量数据设计模型。您将集成这些模型为客户提供服务，通过数据，建模和客户反馈来完成闭环。您对模型的选择需要能够平衡业务指标和响应时间的需求。 Key job responsibilities 基本要求 正在攻读计算机工程，计算机科学，AI，机器学习，运筹学，统计或相关领域的硕士或博士学位。 有AI，ML实验设计和统计分析的经验。 有使用代码和工具实现算法的经验。 至少能熟练地使用一种编程语言（例如Python，Java，C ++等）编码和解决问题。 加分项： 在顶级会议或者期刊上有论文发表。 技术视野好；能与技术团队成员深入讨论概念和算法，并对应用问题提出恰当的解决方案。 出色的批判性思维能力；能以口头和书面形式清楚地向团队沟通您的技术方案。
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 newsletter

Amazon.com | Conditions of Use | Privacy | © 1996-2026 Amazon.com, Inc. or its affiliates

Social