Social
Conversational AI

A quick guide to Amazon’s 50-plus papers at EMNLP 2024

Large language models predominate, both as a research subject themselves and as tools for researching topics of particular interest to Amazon, such as speech, recommendations, and information retrieval.

By Staff writer
November 14, 2024
7 min read
Share

Large language models (LLMs) have come to dominate the field of natural-language processing, so it’s no surprise that they also dominate the research that Amazon scientists are presenting at this year’s Conference on Empirical Methods in Natural-Language Processing (EMNLP). LLM training is the topic with the greatest number of Amazon papers, followed closely by strategies for mitigating misinformation in LLMs’ outputs — including but not limited to hallucinations. At the same time, a number of papers apply LLMs to topics of traditional interest at Amazon, such as speech, recommender systems, and information retrieval. (Papers marked with asterisks were accepted to Findings of EMNLP.)

AI agents

MARCO: Multi-agent real-time chat orchestration
Anubhav Shrimal, Shervin Malmasi, Kriti Biswas, Swarnalatha Raghuraman, Anish Nediyanchath, Yi Zhang, Promod Yenigalla

Code generation

CodeFort: Robust training for code generation models
Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

Socratic human feedback (SoHF): Expert steering strategies for LLM code generation
Subramanian Chidambaram, Erran Li, Min Bai, Xiaopeng LI, Kaixiang Lin, Xiong Zhou, Alex C. Williams

Structured object language modeling (SoLM): Native structured objects generation conforming to complex schemas with self-supervised denoising
Amir Tavanaei, Kee Kiat Koo, Hayreddin Ceker, Shaobai Jiang, Qi Li, Julien Han, Karim Bouyarmane

Contrastive decoding

Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung

Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM.png
Given a simple question with clues, contrastive decoding could have an “obvious blindness” (e.g., assigning higher probability to an uncommon answer, such as "invertebrate", than to the most obvious answer, "bees"). In contrast, the asymptotic probability decoding proposed in "Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM" correctly assigns the highest probability to "bees" by leveraging the probabilities from multiple LMs of different sizes.

Data integration

ASTRA: Automatic schema matching using machine translation
Tarang Chugh, Deepak Zambre

Learning from natural language explanations for generalizable entity matching
Somin Wadhwa, Adit Krishnan, Runhui Wang, Byron C. Wallace, Chris (Luyang) Kong

Pretraining and finetuning language models on geospatial networks for accurate address matching
Saket Maheshwary, Arpan Paul, Saurabh Sohoney

Retrieval augmented spelling correction for e-commerce applications
Xuan Guo, Rohit Patki, Dante Everaert, Christopher Potts

Dataset distillation

Textual dataset distillation via language model embedding
Yefan Tao, Chris (Luyang) Kong, Andrey Kan, Laurent Callot

Textual dataset distillation via language model embedding: DaLLME.png
The DaLLME framework proposed in "Textual dataset distillation via language model embedding" begins by using a language model to transform raw textual data into embedding vectors. A set of distilled vectors is then derived in the embedding space, through a process designed to encapsulate maximum informational content. Finally, the vec2text model translates these distilled vectors back into textual form.

Document understanding

DocKD: Knowledge distillation from LLMs for open-world document understanding models
Sungnyun Kim, Haofu Liao, Srikar Appalaraju, Peng Tang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Stefano Soatto

Information retrieval

Evaluating D-MERIT of partial-annotation on information retrieval
Royi Rassin, Yaron Fairstein, Oren Kalinsky, Guy Kushilevitz, Nachshon Cohen, Alexander Libov, Yoav Goldberg

Identifying high consideration e-commerce search queries
Zhiyu Chen, Jason Choi, Besnik Fetahu, Shervin Malmasi

Learning when to retrieve, what to rewrite, and how to respond in conversational QA*
Nirmal Roy, Leonardo Ribeiro, Rexhina Blloshmi, Kevin Small

Natural-language understanding

Intent detection in the age of LLMs
Gaurav Arora, Shreya Jain, Srujana Merugu

Intent detection in the age of LLMs.png
"Intent detection in the age of LLMs" proposes a methodology for adaptive in-context learning and chain-of-thought-based intent detection using LLMs.

Predicting entity salience in extremely short documents
Ben Bullough, Harrison Lundberg, Chen Hu, Weihang Xiao

LLM evaluation

AXCEL: Automated eXplainable consistency evaluation using LLMs*
P Aditya Sreekar, Sahil Verma, Suransh Chopra, Sarik Ghazarian, Abhishek Persad, Narayanan Sadagopan

Precise model benchmarking with only a few observations
Riccardo Fogliato, Pratik Patil, Nil-Jana Akpinar, Mathew Monfort

LLM fine tuning

AdaZeta: Adaptive zeroth-order tensor-train adaption for memory-efficient large language models fine-tuning
Yifan Yang, Kai Zhen, Ershad Banijamali, Thanasis Mouchtaris, Zheng Zhang

RoseLoRA: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning
Haoyu Wang, Tianci Liu, Ruirui Li, Monica Cheng, Tuo Zhao, Jing Gao

RoseLoRA.png
The row- and column-wise sparse low-rank adaptation (RoseLoRA) framework proposed in "RoseLoRA: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning".

LLMs for speech

Speechworthy instruction-tuned language models
Hyundong Cho, Nicolaas Jedema, Leonardo Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, Jonathan May

LLM misinformation mitigation

ECON: On the detection and resolution of evidence conflicts
Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang

Generative subgraph retrieval for knowledge graph–grounded dialog generation
Jinyoung Park, Minseok Joo, Joo-Kyung Kim, Hyunwoo J. Kim

HalluMeasure: Fine-grained hallucination measurement using chain-of-thought reasoning
Shayan Ali Akbar, Md Mosharaf Hossain, Tess Wood, Si-Chi Chin, Erica Salinas, Victor Alvarez, Erwin Cornejo

Knowledge-centric hallucination detection
Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Zheng Zhang, Yue Zhang

LLM reasoning

Auto-evolve: Enhancing large language model’s performance via self-reasoning framework*
Krishna Aswani, Alex Lu, Pranav Patankar, Priya Dhalwani, Iris Tan, Jayant Ganeshmohan, Simon Lacasse

LLM self-correction

LLM self-correction with DeCRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

DeCRIM.png
In the DeCRIM pipeline proposed in "LLM self-correction with DeCRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints", an LLM first generates a response to a user request. The Decomposer then breaks down the request into granular constraints, and the Critic model gives feedback on whether the response meets those constraints. If it does, the response is output; if not, the LLM uses the feedback to refine the response.

LLM training

Dancing in chains: Reconciling instruction following and faithfulness in language models
Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

DEM: Distribution edited model for training with mixed data distributions
Dhananjay Ram, Aditya Rawal, Momchil Hardalov, Nikolaos Pappas, Sheng Zha

DEM: Distribution Edited Model for Training with Mixed Data Distributions
The distribution-edited model (ΘD) described in "DEM: Distribution edited model for training with mixed data distributions" results from fine-tuning a pretrained model (Θ) on n individual data distributions (Di) and combining the resulting models with basic element-wise vector operations. Here, the extracted distribution vectors (∆ΘDi ) are multiplied by weight coefficients, and the weighted sum is added to the base model.

Evolutionary contrastive distillation for language model alignment
Julian Katz-Samuels, Zheng Li, Hyokun Yun, Priyanka Nigam, Yi Xu, Vaclav Petricek, Bing Yin, Trishul Chilimbi

Hop, skip, jump to convergence: Dynamics of learning rate transitions for improved training of large language models
Shreyas Subramanian, Vignesh Ganapathiraman, Corey Barrett

Learning from relevant subgoals in successful dialogs using iterative training for task-oriented dialog systems
Magdalena Kaiser, Patrick Ernst, Gyuri Szarvas

Quality matters: Evaluating synthetic data for tool-using LLMs
Shadi Iskander, Nachshon Cohen, Zohar Karnin, Ori Shapira, Sofia Tolmach

Query autocompletion

AmazonQAC: A large-scale, naturalistic query autocomplete dataset
Dante Everaert, Rohit Patki, Tianqi Zheng, Christopher Potts

DiAL: Diversity aware listwise ranking for query auto-complete
Sonali Singh, Sachin Farfade, Prakash Mandayam Comar

Question answering

RAG-QA arena: Evaluating domain robustness for long-form retrieval-augmented question answering
Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

Retrieving contextual information for long-form question answering using weak supervision
Philipp Christmann, Svitlana Vakulenko, Ionut Teodor Sorodoc, Bill Byrne, Adrià de Gispert

Recommender systems

Efficient pointwise-pairwise learning-to-rank for news recommendation
Nithish Kannen Senthilkumar, Yao Ma, Gerrit van den Burg, Jean Baptiste Faddoul

Efficient pointwise-pairwise learning-to-rank for news recommendation.png
An illustration of the GLIMPSE framework proposed in "Efficient pointwise-pairwise learning-to-rank for news recommendation". GLIMPSE adopts a multitask approach in which a pretrained language model is fine-tuned on both the relevance prediction task and the pairwise-preference task. During inference, the relevance predictions are used to produce an initial pointwise ranking, which is subsequently improved by one or more right-to-left (RTL) passes using pairwise comparisons.

PEARL: Preference extraction with exemplar augmentation and retrieval with LLM agents
Vijit Malik, Akshay Jagatap, Vinayak Puranik, Anirban Majumder

Sequential LLM framework for fashion recommendation
Han Liu, Xianfeng Tang, Tianlang Chen, Jiapeng Liu, Indu Indu, Henry Peng Zou, Peng Dai, Roberto Fernandez Galan, Mike Porter, Dongmei Jia, Ning Zhang, Lian Xiong

Responsible AI

Attribute controlled fine-tuning for large language models: A case study on detoxification
Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris

FLIRT: Feedback loop in-context red teaming
Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta

Order of magnitude speedups for LLM membership inference
Rongting Zhang, Martin Bertran Lopez, Aaron Roth

Synthetic data generation

CorrSynth: A correlated sampling method for diverse dataset generation from LLMs
Suhas Kowshik, Abhishek Divekar, Vijit Malik

A Correlated Sampling Method for Diverse Dataset Generation from LLMs
"CorrSynth: A correlated sampling method for diverse dataset generation from LLMs" introduces a sampling method that uses anti-correlation between examples rather than few-shot generation.

DATA ADVISOR: Dynamic data curation for safety alignment of large language models
Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan

Evaluating differentially private synthetic data generation in high-stakes domains
Krithika Ramesh, Nupoor Gandhi, Pulkit Madaan, Lisa Bauer, Charith Peris, Anjalie Field

SYNTHESIZRR: Generating diverse datasets with retrieval augmentation
Abhishek Divekar, Greg Durrett

Abstract depiction of the SYNTHESIZRR procedure
Abstract depiction of the procedure proposed in "SYNTHESIZRR: Generating diverse datasets with retrieval augmentation". The content sourcing stage retrieves K unique documents {r1,...,rK} from a large corpus for each in-context covariate xICL. The task-inversion stage uses a parameterized context refinement prompt, Pτ, which takes parameters Rinv (inversion instruction), rk (a retrieved document), and V(yICL) (the verbalized target label). A generalist teacher LLM autoregressively generates a synthetic covariate. Each in-context example thus produces K unique synthetic examples {x̃1,..., x̃K}, which we include in the dataset with target yICL.

Text classification

Distance-aware calibration for pre-trained language models*
Alberto Gasparin, Gianluca Detommaso

Performance-guided LLM knowledge distillation for efficient text classification at scale

Flavio Di Palo, Prateek Singhi, Bilal Fadlallah

Prompt-tuned muti-task taxonomic transformer (PTMTTaxoFormer)
Rajashekar Vasantha, Nhan Nguyen, Yue Zhang

Text summarization

Salient information prompting to steer content in prompt-based abstractive summarization
Lei Xu, Asad Karim, Saket Dingliwal, Aparna Elangovan

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Research Scientist, Selling Partner Satisfaction
US, WA, Seattle
We’re looking for a Research Scientist to join a team that measures and explains how over 2.4 million sellers and vendors experience selling on Amazon. You’ll apply survey science, psychometrics, and applied statistics to help drive meaningful change at Amazon on behalf of Sellers. In this role, you’ll work across a variety of research methodologies to optimize our data collection, create scalable analytical approaches, and deep dive the Seller experience to create rigorous, quantitative insights that senior leaders use to set strategy. Key job responsibilities Key Job Responsibilities - Apply psychometric and survey methodology techniques (e.g., IRT, factor analysis, scale development, single-item indicators) to measure seller experience constructs with scientific rigor - Design and implement frameworks that link seller attitudinal data to behavioral outcomes and identify high-impact opportunity areas - Design and execute statistical analyses including regression modeling, significance testing, and driver analysis to identify what matters most to sellers - Apply observational causal evaluation methods to estimate the effects of policy changes, product launches, and platform interventions on seller experience - Design, build and maintain analytical pipelines that transform raw survey data into production-ready metrics, reports, and dashboards - Design and build systems to analyze open-ended survey responses using text classification, thematic coding, and natural language processing techniques - Design and monitor processes improve survey response rates, sampling methodology, and data quality - Productionalize research code: take analyses from prototype to automated, reproducible pipelines that run reliably in production environments - Communicate findings clearly to technical and non-technical audiences through written reports, data visualizations, and presentations - Collaborate and influence with cross-functional partners to translate business questions into well-defined research problems and scientific metrics - Document research methods, assumptions, and limitations transparently to ensure reproducibility A day in the life Your day typically starts with the data. You might spend the morning reviewing satisfaction trends, investigating a shift in a key metric, and pulling together an analysis that explains what's driving it. You'll regularly meet with external teams to help them understand how a proposed product will affect seller sentiment and what the data says they should prioritize. You'll also spend time in R or Python building, training, or testing models to improve how we measure and act on sentiment data. About the team Our team owns the research and measurement infrastructure that tracks satisfaction across all 2.1 million selling partners on Amazon, spanning Seller Central, Next Gen Selling, and Mobile. We sit at the intersection of data and strategy, partnering with teams across product, design, and engineering to advocate for seller experience improvements. This is a high-visibility team where the work is consequential, the stakeholders are senior, and the problems are genuinely hard.
Data Scientist , Worldwide Global Selling -AIT
CN, 31, Shanghai
Worldwide Global Selling has been helping individuals and businesses increase sales and reach new customers around the globe. Today, more than 50% of Amazon's total unit sales come from third-party selection. The Global Selling team in China is responsible for recruiting local businesses to sell on Amazon's 19+ overseas marketplaces and supporting local Sellers' success and growth on Amazon. Our vision is to be the first choice for all types of Chinese business to go globally. The Worldwide Global Selling Analytics, Intelligence, and Technology (WWGS-AIT) team serves as the research, automation, and insight arm of the International Seller Service data hub, enabling rapid delivery of growth insights through strategic investments in regional data foundations, self-service business intelligence solutions, and artificial intelligence tools. The WWGS-AIT team is positioned to establish AI-ready foundational capabilities across the WWGS organization while maintaining excellence in business insight generation, and self-service BI/AI application development. WWGS-AIT is looking for a Data Scientist to design and build seller-facing AI agents that turn our AI-ready data foundation into intelligent, conversational experiences for Amazon's global sellers. You will own the intelligence layer of these agents end-to-end, from modeling and retrieval to evaluation and launch, working alongside applied scientists, data engineers, and the Seller Assistant platform team to put trustworthy AI directly into sellers' hands. Key job responsibilities - Design, build, and iterate seller-facing AI agents (LLM-powered) that help Chinese sellers grow globally, reasoning over WWGS-AIT's AI-ready data foundation and knowledge base. - Develop the intelligence layer of agents: retrieval-augmented generation (RAG) over our knowledge management system, tool-use / function-calling orchestration, prompt engineering, and model fine-tuning or adaptation where needed. - Ground agent responses in standardized metrics and unified seller profiles to guarantee consistency and accuracy across agents; design and enforce guardrails that prevent hallucination and protect sensitive, compliance-restricted data. - Build rigorous evaluation frameworks (golden datasets, offline evaluation, and online experimentation) to measure and continuously improve agent quality, safety, and seller impact. - Develop seller-intelligence models (segmentation, entity resolution / One-ID, ranking and recommendation) that power personalized agent experiences. - Partner with WWGS Tech and the Seller Assistant platform team to productionize agents and tools (e.g., via MCP), defining the model and intelligence contract while engineering operates the runtime. - Collaborate with business, product, and cross-functional partners to translate seller pain points into agent capabilities and measurable business outcomes. - Stay current with advances in GenAI and agentic systems, and bring applied research into production.
Data Scientist, Automated Vehicle Testing
US, WA, Redmond
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. We are looking for an experienced Data Scientist to help architect state-of-the-art test infrastructure and lead the development of data models and analysis tools to represent the ground truth about satellite test results in order to facilitate important business decisions. Our team is responsible for core infrastructure and tools that will serve as the backbone of automated satellite testing operations to enable rapid scaling of manufacturing processes. Key job responsibilities * Work with engineering, software and manufacturing teams to understand drivers, impacts, and key influences on satellite performance * Lead the design, build and implementation of production models and make decisions in real time for satellite test results * Drive actions at scale to optimize test methodology and drive increases to satellite reliability * Analysis and modeling of satellite telemetry from test results in lab and on-orbit * Develop models and data pipelines for satellite telemetry * Create and manage datasets for continued pre-training and supervised fine-tuning of LLMs * Develop scalable visualizations for analysis of satellite performance A day in the life As Amazon Leo Data Scientist you will own the architecture definition and development of data analysis tools to to aid engineering and production teams in deciding flight-worthiness of each Amazon Leo satellite and historical traceability tools to enable simplified discovery and interpretation of past test data. You will work with multiple engineering, software and manufacturing teams across ground and space systems, to specify requirements, define data collection, interpretation strategies, data pipelines and implement data analysis and reporting tools for Integrated Vehicle tests. Your focus will be in optimizing the analysis of test results to enable Amazon Leo production plans. About the team The Automated Vehicle Testing Team is a mix of scientists and software engineers responsible for data infrastructure, tools, and research that serve as the backbone of automated satellite testing operations to enable rapid scaling of manufacturing processes.
Senior Economist, PXT Central Science
US, CA, San Francisco
The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. We are looking for a Senior Economist who is able to provide structure around complex business problems, hone those complex problems into specific, scientific questions, and test those questions to generate insights. The ideal candidate will work with various science, engineering, operations, and analytics teams to estimate models and algorithms on large scale data, design pilots and measure their impact, and transform successful prototypes into improved policies and programs at scale. They will lead teams of researchers to produce robust, objective research results and insights which can be communicated to a broad audience inside and outside of Amazon. The ideal candidate has a PhD in Economics and deep expertise in causal inference and applied econometrics. Experience with large-scale data, proficiency in statistical programming (Python), and familiarity with machine learning methods are a plus. To be successful in this role, you should be comfortable operating with ambiguity, able to independently scope and prioritize research agendas, skilled at influencing decisions through rigorous analysis, and comfortable with using AI tools.
Sr. Manager, Applied Science, AWS Agentic AI
US, WA, Seattle
Amazon Web Services (AWS) is looking for a sr. Manager, Applied to join the Quick Science team. Quick is AWS’s enterprise generative AI assistant that helps users answer questions, summarize documents, generate content, take actions, and automate workflows using information across enterprise systems. As a key member of this team, you will lead research and development efforts in generative AI and Agentic AI to enable intelligent agents that perform complex reasoning, automate multi-step workflows, and make enterprise users significantly more productive. Key job responsibilities You’ll work on building and optimizing multi-modal foundation models, training and fine-tuning state-of-the-art LLMs, and architecting systems that scale efficiently across domains. This role blends science leadership, development of applied scientists, innovation, and deep collaboration with engineering teams to bring research into production.
Data Scientist , Leo Customer Terminal
US, WA, Redmond
At Amazon, we’re inventing on behalf of customers, and with Amazon Leo, we’re redefining what global connectivity looks like. Our mission is to deliver fast, affordable broadband to unserved and underserved communities around the world through a constellation of low Earth orbit (LEO) satellites. Every system we build helps connect people to education, healthcare, opportunity, and each other. As a Data Scientist, you will be responsible for developing advanced analytics and machine learning solutions for user terminals. You will develop predictive models to proactively identify possible user terminal failures in the field. You will work in a collaborative environment with a multi-disciplinary team, including constellation, RF, antenna, silicon, algorithm, and software engineers. Key job responsibilities As a Data Scientist, you will develop analytic tools for a team developing current and future user terminals. Your responsibilities include: • Develop statistical and analytical tool to enable the regression decision from on-orbit and lab measurement of user terminals • Publish documents and create compelling visualizations and presentations to communicate insights to stakeholders • Create and manage datasets for continued pre-training and supervised fine-tuning of LLMs • Develop scalable visualizations for analysis of user terminal performance • Work closely with constellation, RF, antenna, silicon, algorithm, and software engineers to root-cause the failures using data as the primary tool • Drive consensus on metrics and analysis approaches to support product development strategy 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. A day in the life As a Data Scientist in the LEO Customer Terminal Team, you will work daily with satellite constellation, algorithm, RF, antenna, silicon, hardware, and software teams in a collaborative environment. Your focus will be using data as an intelligence source to enable design decisions for the team. About the team The LEO Customer Terminal team is responsible for developing both outdoor and indoor devices that enable customers to access internet service via the LEO satellite network. We own the entire process from early prototypes through mass production, including requirements documentation, architecture definition, hardware development, algorithm development, and all integration and verification testing.
Research Scientist II - AMZ9898222
US, NY, New York
MULTIPLE POSITIONS AVAILABLE Employer: AMAZON.COM SERVICES LLC Offered Position: Research Scientist II Job Location: New York, New York Job Number: AMZ9898222 Position Responsibilities: Interact with various software and business groups to develop an understanding of their business requirements and operational processes. Utilize acquired knowledge and business judgment to build scalable machine learning systems, optimization models and operational tools to improve the bottom line. Build quantitative mathematical models to represent a wide range of supply chain, transportation and logistics systems. Implement these models and tools using modeling languages and engineering code in software languages such as Python, C++, or JAVA. Gather required data for analysis and mathematical model building by writing ad-hoc scripts and database queries. Perform quantitative, economic, and numerical performance analyses of these systems under uncertainty using statistical and optimization tools. Create computer simulations to support operational decision-making. Identify areas with potential for improvement and work with internal teams to generate requirements to realize improvements. Design optimal or near optimal solution methodologies to be used by in-house decision support tools and software. Create software prototypes to verify and validate the devised solutions methodologies. Integrate prototypes into production systems using standard software development tools and methodologies. Position Requirements: Master's degree or foreign equivalent degree in Operations Research, Computer Science, Engineering, Mathematics, or a related field and one year of research or work experience in the job offered, or as a Research Scientist, Research Assistant, Software Engineer, or a related occupation. Employer will accept a Bachelor's degree or foreign equivalent degree in Operations Research, Computer Science, Engineering, Mathematics, or a related field and five years of progressive post-baccalaureate research or work experience in the job offered or a related occupation as equivalent to the Master's degree and one year of experience. Must have one year of research or work experience in the following skill(s): (1) programming with a major programming language including Java, C++, C#, C, or Python; and (2) formulating and solving both discrete and continuous optimization problems. Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation. 40 hours / week, 8:00am-5:00pm, Salary Range $158,440/year to $212,800/year. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, visit: https://www.aboutamazon.com/workplace/employee-benefits.#0000
Applied Scientist I, CMT
IN, TN, Chennai
As a member of the CMT team, you'll play a key role in the evolution of our Competitive Monitoring systems to solve significantly complex and interesting technical challenges in machine learning, large language models in production, and recommender systems to name a few. The team's work directly impacts customer experience at a worldwide scale. Key job responsibilities Key job responsibilities 1. Research the problem domain and come up with various approaches to solve the problem. 2. Be willing to experiment quickly and fail fast. 3. Collaborate with engineers to come up with the right end to end solution to the business problems. 4. Ideate on future roadmap for science in CMT 5. Be willing to roll up your sleeves and learn core topics outside applied science, for example ML engineering A day in the life A typical day might involve (a) working on ideas for improving models around product similarity or price recommendations, (b) working closely with other scientists and our ML engineers to ensure that the best models are in production, (c) writing good maintainable code that can be reused and reproduced, (d) sharing your work across CMT and beyond via technical writings and presentations
Applied Scientist III, Sponsored Products and Brands - Advertiser Growth and Strategies
US, WA, Seattle
The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through cutting-edge generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising. We are looking for an Applied Scientist III to set the scientific direction for the next generation of agentic AI applications that guide Amazon advertisers. In this role you will define, lead and build the science behind agentic systems that reason, plan, and act autonomously to manage and optimize ad campaigns based on a deep understanding of the advertiser and the marketplace. You will own the agentic architecture end to end, partnering closely with product and engineering leaders to translate a long-term science vision into concrete research and engineering roadmaps. Working backwards from the needs of millions of advertisers, you will take the lead on medium-to-large, ambiguous problems where neither the problem nor the solution is well defined, and deliver customer-facing products that help advertisers create, optimize, and grow their campaigns. You will invent new methods at the product level, and drive their adoption across multiple teams. This role combines science leadership, technical depth, product focus, and business understanding: you will raise the science bar, build consensus on approach across partners, and mentor scientists and engineers while remaining deeply hands-on with the hardest technical problems. Key job responsibilities As an Applied Scientist III on this team you will: - Define the science vision for the agentic campaign management system and, with product and engineering leaders, turn it into delivery roadmaps. - Build agentic systems that autonomously manage and optimize ad campaigns — encoding auction and marketplace dynamics (bidding, budget pacing, keyword and targeting decisions) while balancing advertiser ROI, shopper experience, and marketplace health. - Define and curate the datasets and signals needed to train and evaluate these agents — advertiser and campaign data, auction and bid/budget signals, impressions, clicks, conversions, and search-term/keyword performance. - Stay deeply hands-on: write production-quality, critical-path code and build core components that take agentic systems from prototype to launch. - Own the agentic architecture — planning, tool use and integration (e.g., MCP), long-horizon reasoning (e.g., ReAct, CoT/ToT), and multi-agent orchestration — and stay deeply hands-on, writing production-quality, critical-path code from prototype to launch. - Define the evaluation and safety methodology for agent workflows and drive its adoption as the bar for reliability and trust. - Drive the team's scientific agenda, mentor scientists and engineers, and represent the team in the internal and external scientific community. About the team The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through the latest generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising. This team within Sponsored Products and Brands is focused on guiding and supporting millions of advertisers to meet their advertising needs of creating and managing ad campaigns. At this scale, the complexity of diverse advertiser goals, campaign types, and market dynamics creates both a massive technical challenge and a transformative opportunity: even small improvements in guidance systems can have outsized impact on advertiser success and Amazon’s retail ecosystem. Our vision is to build a highly personalized, context-aware agentic advertiser guidance system that leverages LLMs together with tools such as auction simulations, ML models, and optimization algorithms. This agentic framework, will operate across both chat and non-chat experiences in the ad console, scaling to natural language queries as well as autonomously manage campaigns based on deep understanding of the advertiser. To execute this vision, we collaborate closely with stakeholders across Ad Console, Sales, and Marketing to identify opportunities—from high-level product guidance down to granular keyword recommendations—and deliver them through a tailored, personalized experience. Our work is grounded in state-of-the-art agent architectures, tool integration, reasoning frameworks, and model customization approaches (including tuning, MCP, and preference optimization), ensuring our systems are both scalable and adaptive.
Sr. Applied Scientist, Sponsored Products and Brands Agent
US, NY, New York
The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising. About the team SPB Agent team's vision is to build a highly personalized and context-aware agentic advertiser guidance system that seamlessly integrates Large Language Models (LLMs) with sophisticated tooling, operating across all experiences. The SPB-Agent is the central agent that interfaces with advertisers across Ads Console, Selling Partner portals (Seller Central, KDP, Vendor Central), and internal Sales systems. We identify high-impact opportunities spanning from strategic product guidance to granular optimization and deliver them through personalized, scalable experiences grounded in state-of-the-art agent architectures, reasoning frameworks, sophisticated tool integration, and model customization approaches including fine-tuning, MCP, and preference optimization. This presents an exceptional opportunity to shape the future of e-commerce advertising through advanced AI technology at unprecedented scale, creating solutions that directly impact millions of advertisers.
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