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
Member of Technical Staff, AI Product Manager, AGI Autonomy
US, MA, Boston
We're a new research lab based in San Francisco and Boston focused on developing foundational capabilities for useful AI agents. We're pursuing several key research bets that will enable AI agents to perform real-world actions, learn from human feedback, self-course-correct, and infer human goals. We're particularly excited about combining large language models (LLMs) with reinforcement learning (RL) to solve reasoning and planning, learned world models, and generalizing agents to physical environments. We're a small, talent-dense team with the resources and scale of Amazon. Each team has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research. AI agents are the next frontier—the right research bets can reinvent what's possible. Join us and help build this lab from the ground up. Key job responsibilities * Define the product vision and roadmap for our agentic developer platform, translating research into products developers love * Partner deeply with research and engineering to identify which capabilities are ready for productization and shape how they're exposed to customers * Own the developer experience end-to-end from API design and SDK ergonomics to documentation, sample apps, and onboarding flows * Understand our customers deeply by engaging directly with developers and end-users, synthesizing feedback, and using data to drive prioritization * Shape how the world builds AI agents by defining new primitives, patterns, and best practices for agentic applications About the team Our team brings the AGI Lab's agent capabilities to customers. We build accessible, usable products: interfaces, frameworks, and solutions, that turn our platform and model capabilities into AI agents developers can use. We own the Nova Act agent playground, Nova Act IDE extension, Nova Act SDK, Nova Act AWS Console, reference architectures, sample applications, and more.
Senior Applied Scientist, Navigation
US, CA, San Francisco
Amazon is on a mission to redefine the future of automation — and we're looking for exceptional talent to help lead the way. We are building the next generation of advanced robotic systems that seamlessly blend cutting-edge AI, sophisticated control systems, and novel mechanical design to create adaptable, intelligent automation solutions capable of operating safely alongside humans in dynamic, real-world environments. At Amazon, we leverage the power of machine learning, artificial intelligence, and advanced robotics to solve some of the most complex operational challenges at a scale unlike anywhere else in the world. Our fleet of robots spans hundreds of facilities globally, working in sophisticated coordination to deliver on our promise of customer excellence — and we're just getting started. As a Sr. Scientist in Robot Navigation, you will be at the forefront of this transformation — architecting and delivering navigation systems that are intelligent, safe, and scalable. You will bring deep expertise in learning-based planning and control, a strong understanding of foundation models and their application to embodied agents, and as well as have in-depth understanding of control-theoretic approaches such as model predictive control (MPC)-based trajectory planning. You will develop navigation solutions that seamlessly blend data-driven intelligence with principled control-theoretic guarantees. Our vision is bold: to build navigation systems that allow robots to move fluidly and safely through dynamic environments — understanding context, anticipating change, and adapting in real time. You will lead research that bridges the gap between cutting-edge academic advances and production grade deployment, collaborating with world-class teams pushing the boundaries of robotic autonomy, manipulation, and human-robot interaction. Join us in building the next generation of intelligent navigation systems that will define the future of autonomous robotics at scale. Key job responsibilities - Design, develop, and deploy perception algorithms for robotics systems, including object detection, segmentation, tracking, depth estimation, and scene understanding - Lead research initiatives in computer vision, sensor fusion and 3D perception - Collaborate with cross-functional teams including robotics engineers, software engineers, and product managers to define and deliver perception capabilities - Drive end-to-end ownership of ML models — from data collection and labeling strategy to training, evaluation, and deployment - Mentor junior scientists and engineers; contribute to a culture of technical excellence - Define and track key metrics to measure perception system performance in real-world environments - Publish research findings in top-tier venues (CVPR, ICCV, ECCV, ICRA, NeurIPS, etc.) and contribute to patents A day in the life - Train ML models for deployment in simulation and real-world robots, identify and document their limitations post-deployment - Drive technical discussions within your team and with key stakeholders to develop innovative solutions to address identified limitations - Actively contribute to brainstorming sessions on adjacent topics, bringing fresh perspectives that help peers grow and succeed — and in doing so, build lasting trust across the team - Mentor team members while maintaining significant hands-on contribution to technical solutions About the team Our team is a group is a diverse group of scientists and engineers passionate about building intelligent machines. We value curiosity, rigor, and a bias for action. We believe in learning from failure and iterating quickly toward solutions that matter.
Applied Scientist II, Advertising Incrementality Measurement
US, NY, New York
Do you want to lead the Ads industry and redefine how we measure the effectiveness of Amazon Ads business? Are you passionate about causal inference, Deep Learning & AI, raising the science bar, and connecting leading-edge science research to Amazon-scale implementation? If so, come join Amazon Ads to be a science leader within our Advertising Incrementality Measurement science team! Our work builds the foundations for providing customer-facing advertising measurement tools, furthering internal research & development, and building out Amazon's advertising measurement offerings. Incrementality is a lynchpin for the next generation of Amazon Advertising measurement solutions, and this role will play a key role in the release and expansion of these offerings. We are looking for a thought leader that has an aptitude for delivering customer-focused solutions and who enjoys working on the intersection of Big-Data analytics, Machine/Deep Learning, and Causal Inference. A successful candidate will be a self-starter, comfortable with ambiguity, able to think big and be creative, while still paying careful attention to detail. You should be able to translate how data represents the customer journey, be comfortable dealing with large and complex data sets, and have experience using machine learning and/or econometric modeling to solve business problems. You should have strong analytical and communication skills, be able to work with product managers to define key business questions and work with the engineering team to bring our solutions into production. You will join a highly collaborative and diverse working environment that will empower you to shape the future of Amazon advertising, and also allow you to become part of our large science community. Key job responsibilities • Apply expertise in ML/DL, AI, and causal modeling to develop new models that describe how advertising impacts customers’ actions • Own the end-to-end development of novel scientific models that address the most pressing needs of our business stakeholders and help guide their future actions • Improve upon and simplify our existing solutions and frameworks • Review and audit modeling processes and results for other scientists, both junior and senior • Work with leadership to align our scientific developments with the business strategy • Identify new opportunities that are suggested by the data insights • Bring a department-wide perspective into decision making • Develop and document scientific research to be shared with the greater science community at Amazon About the team AIM is a cross disciplinary team of engineers, product managers, economists, data scientists, and applied scientists with a charter to build scientifically-rigorous causal inference methodologies at scale. Our job is to help customers cut through the noise of the modern advertising landscape and understand what actions, behaviors, and strategies actually have a real, measurable impact on key outcomes. The data we produce becomes the effective ground truth for advertisers and partners making decisions affecting millions in advertising spend.
Data Scientist, ADE Analytics
CA, BC, Vancouver
The Alexa Daily Essentials team delivers experiences critical to how customers interact with Alexa as part of daily life. Alexa users engage with our products across experiences connected to Timers, Alarms, Calendars, Food, and News. Our experiences include critical time saving techniques, ad-supported news audio and video, and in-depth kitchen guidance aimed at serving the needs of the family from sunset to sundown. As a Data Scientist on our team, you'll work with complex data, develop statistical methodologies, and provide critical product insights that shape how we build and optimize our solutions. You will work closely with your Analytics and Applied Science teammates. You will build frameworks and mechanisms to scale data solutions across our organization. If you are passionate about redefining how AI can improves everyone's daily life, we’d love to hear from you. Key job responsibilities Problem-Solving - Analyze complex data to identify patterns, inform product decisions, and understand root causes of anomalies. - Develop analysis and modeling approaches to drive product and engineering actions to identify patterns, insights, and understand root causes of anomalies. Your solutions directly improve the customer experience. - Independently work with product partners to identify problems and opportunities. Apply a range of data science techniques and tools to solve these problems. Use data driven insights to inform product development. Work with cross-disciplinary teams to mechanize your solution into scalable and automated frameworks. Data Infrastructure - Build data pipelines, and identify novel data sources to leverage in analytical work - both from within Alexa and from cross Amazon - Acquire data by building the necessary SQL / ETL queries Communication - Excel at communicating complex ideas to technical and non-technical audiences. - Build relationships with stakeholders and counterparts. Work with stakeholders to translate causal insights into actionable recommendations - Force multiply the work of the team with data visualizations, presentations, and/or dashboards to drive awareness and adoption of data assets and product insights - Collaborate with cross-functional teams. Mentor teammates to foster a culture of continuous learning and development
Member Technical Staff - Software Development, Frontier AI Robotics
US, CA, San Francisco
In this role, you will act as the primary specialist for physics engine internals and dynamics, developing high-fidelity, vectorized simulation environments for robotics locomotion, navigation, and interaction/manipulation. You will collaborate with hardware engineers to validate robot models and partner with research scientists to ensure numerical stability and physical accuracy for Sim2Real transfer. Your work focuses on tuning solvers, optimizing collision dynamics, and performing system identification to enable the training of robust robot control policies for complex, physical interactions. Key job responsibilities * Develop and maintain the shared simulation software framework, specifically owning the physics integration, robot state management, and control layers * Develop and optimize parallelized (vectorized) physics environments for high-throughput reinforcement learning (e.g., Isaac Lab, MuJoCo) * Tune physics engine parameters (solvers, friction, restitution) to support complex contact-rich scenarios required for dexterous manipulation and agile locomotion. * Implement and validate complex robot models (URDF/MJCF) involving precise actuator and sensor modeling * Collaborate with robot engineers and scientists to perform System Identification (SysID) to minimize the Sim2Real gap About the team At Frontier AI & Robotics (FAR), we're not just advancing robotics – we're reimagining it from the ground up. Our team is building the future of intelligent robotics through frontier foundation models and end-to-end learned systems. We tackle some of the most challenging problems in AI and robotics, from developing sophisticated perception systems to creating adaptive manipulation strategies that work in complex, real-world scenarios. What sets us apart is our unique combination of ambitious research vision and practical impact. We leverage Amazon's massive computational infrastructure and rich real-world datasets to train and deploy state-of-the-art foundation models. Our work spans the full spectrum of robotics intelligence – from multimodal perception using images, videos, and sensor data, to sophisticated manipulation strategies that can handle diverse real-world scenarios. We're building systems that don't just work in the lab, but scale to meet the demands of Amazon's global operations. Join us if you're excited about pushing the boundaries of what's possible in robotics, working with world-class researchers, and seeing your innovations deployed at unprecedented scale.
Senior Applied Scientist, Ad Measurements Science
US, NY, New York
The Ads Measurement Science team in the Measurement, Ad Tech, and Data Science (MADS) team of Amazon Ads serves a centralized role developing solutions for a multitude of performance measurement products. We create solutions which measure the comprehensive impact of advertiser's ad spend, including sales impacts both online and offline and across timescales, and provide actionable insights that enable our advertisers to optimize their media portfolios. We also own the science solutions for AI tools that unlock new insights and automate high-effort customer workflows, such as custom query and report generation based on natural language user requests. We leverage a host of scientific technologies to accomplish this mission, including Generative AI, classical ML, Causal Inference, Natural Language Processing, and Computer Vision. As a Senior Applied Scientist on the team, you will be at the forefront of innovation, developing measurement solutions end-to-end from inception to production. You will set the technical vision and innovate on behalf of our customers. You will propose, design, analyze, and productionize models to provide novel measurement insights to our customers. You will partner with engineering to deploy these solutions into production. You will work with key stakeholders from various business teams to enable advertisers to act upon those metrics. Key job responsibilities * Lead the development of ad measurement models and solutions that address the full spectrum of an advertiser's investment, focusing on scalable and efficient methodologies. * Collaborate closely with cross-functional teams including engineering, product management, and business teams to define and implement measurement solutions. * Use state-of-the-art scientific technologies including Generative AI, Classical Machine Learning, Causal Inference, Natural Language Processing, and Computer Vision to develop state of the art models that measure the impact of ad spend across multiple platforms and timescales. * Drive experimentation and the continuous improvement of ML models through iterative development, testing, and optimization. * Translate complex scientific challenges into clear and impactful solutions for business stakeholders. * Mentor and guide junior scientists, fostering a collaborative and high-performing team culture. * Foster collaborations between scientists to move faster, with broader impact. * Regularly engage with the broader scientific community with presentations, publications, and patents. A day in the life You will solve real-world problems by getting and analyzing large amounts of data, generate business insights and opportunities, design simulations and experiments, and develop statistical and ML models. The team is driven by business needs, which requires collaboration with other Scientists, Engineers, and Product Managers across the advertising organization. You will prepare written and verbal presentations to share insights to audiences of varying levels of technical sophistication. Team video https://advertising.amazon.com/help/G4LNN5YWHP6SM9TJ About the team We are a team of scientists across Applied, Research, Data Science and Economist disciplines. You will work with colleagues with deep expertise in ML, NLP, CV, Gen AI, and Causal Inference with a diverse range of backgrounds. We partner closely with top-notch engineers, product managers, sales leaders, and other scientists with expertise in the ads industry and on building scalable modeling and software solutions.
Applied Scientist II, Brand Registry
CA, ON, Toronto
The Brand Registry team is seeking an Applied Scientist to tackle complex, high-impact problems that directly affect millions of brands, selling partners, and customers on Amazon. You will design, develop, and deploy AI solutions—leveraging large language models (LLMs) and agentic AI frameworks—to power intelligent automation that augments human decision-making and drives autonomous outcomes at scale. What You'll Do -Build agent-based AI systems that reason, plan, and act like domain experts progressing from decision-support tools to fully autonomous solutions -Own the end-to-end ML lifecycle, from problem formulation and data analysis through experimentation, model development, and production deployment -Work backwards from data insights and customer feedback to identify the highest-value science opportunities and translate them into scalable machine learning solutions -Partner closely with product managers and engineering teams to define requirements, iterate rapidly, and launch solutions that deliver measurable business impact -Collaborate with domain experts across Amazon to pioneer innovative approaches to unsolved problems in brand protection and seller experience What We're Looking For -Technical depth: Extensive hands-on experience in Machine Learning, with a strong focus on Generative AI and LLM-based applications (e.g., fine-tuning, prompt engineering, retrieval-augmented generation, multi-agent orchestration) -End-to-end delivery: Proven track record of driving large-scale ML initiatives from conception through production launch in fast-paced, ambiguous environments -Scientific rigor: Strong foundation in experimental design, statistical analysis, and the ability to translate research into production-grade systems -Customer obsession: A bias toward working backwards from real-world problems and customer pain points rather than technology for its own sake -Entrepreneurial mindset: Comfort with ambiguity, a bias for action, and the tenacity to break down complex problems into actionable solutions -Communication skills: Ability to articulate technical concepts clearly to both technical and non-technical stakeholders About the team Brand Registry's mission is bold and unambiguous: protect 100% of the brands in the Amazon catalog. We are the team that stands between authentic brands and the forces that threaten their integrity — counterfeit products, catalog abuse, unauthorized sellers, and inaccurate brand representation. We do this by building the tools, systems, and experiences that empower brand owners to establish, protect, and grow their presence on Amazon with confidence. Achieving this mission requires deep collaboration across science, engineering, legal, and selling partner experience teams — all working in concert to deliver a seamless, trustworthy brand ownership experience at global scale.
Senior Applied Scientist
US, WA, Seattle
At Amazon Selection and Catalog Systems (ASCS), our mission is to power the online buying experience for customers worldwide so they can find, discover, and buy any product they want. We innovate on behalf of our customers to ensure uniqueness and consistency of product identity and to infer relationships between products in Amazon Catalog to drive the selection gateway for the search and browse experiences on the website. We're solving a fundamental AI challenge: establishing product identity and relationships at unprecedented scale. Using Generative AI, Visual Language Models (VLMs), and multimodal reasoning, we determine what makes each product unique and how products relate to one another across Amazon's catalog. The scale is staggering: billions of products, petabytes of multimodal data, millions of sellers, dozens of languages, and infinite product diversity—from electronics to groceries to digital content. The research challenges are immense. GenAI and VLMs hold transformative promise for catalog understanding, but we operate where traditional methods fail: ambiguous problem spaces, incomplete and noisy data, inherent uncertainty, reasoning across both images and textual data, and explaining decisions at scale. Establishing product identities and groupings requires sophisticated models that reason across text, images, and structured data—while maintaining accuracy and trust for high-stakes business decisions affecting millions of customers daily. Amazon's Item and Relationship Platform group is looking for an innovative and customer-focused applied scientist to help us make the world's best product catalog even better. In this role, you will partner with technology and business leaders to build new state-of-the-art algorithms, models, and services to infer product-to-product relationships that matter to our customers. You will pioneer advanced GenAI solutions that power next-generation agentic shopping experiences, working in a collaborative environment where you can experiment with massive data from the world's largest product catalog, tackle problems at the frontier of AI research, rapidly implement and deploy your algorithmic ideas at scale, across millions of customers. Key job responsibilities Key job responsibilities include: * Formulate novel research problems at the intersection of GenAI, multimodal learning, and large-scale information retrieval—translating ambiguous business challenges into tractable scientific frameworks * Design and implement leading models leveraging VLMs, foundation models, and agentic architectures to solve product identity, relationship inference, and catalog understanding at billion-product scale * Pioneer explainable AI methodologies that balance model performance with scalability requirements for production systems impacting millions of daily customer decisions * Own end-to-end ML pipelines from research ideation to production deployment—processing petabytes of multimodal data with rigorous evaluation frameworks * Define research roadmaps aligned with business priorities, balancing foundational research with incremental product improvements * Mentor peer scientists and engineers on advanced ML techniques, experimental design, and scientific rigor—building organizational capability in GenAI and multimodal AI * Represent the team in the broader science community—publishing findings, delivering tech talks, and staying at the forefront of GenAI, VLM, and agentic system research
Member of Technical Staff - Reinforcement Learning (Infrastructure), AGI Autonomy
US, CA, San Francisco
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. 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. In this role, you will work closely with research teams to design, build, and maintain systems for training and evaluating state-of-the-art agent models. Our team works inside the Amazon AGI SF Lab, an environment designed to empower AI researchers and engineers to work with speed and focus. Our philosophy combines the agility of a startup with the resources of Amazon. Key job responsibilities * Develop training infrastructure to ensure large-scale reinforcement learning on LLMs runs highly efficient and robust. * Work across the entire technology stack, including low level ML system, job orchestration and data management. * Analyze, troubleshoot and profiling complex ML systems, identify and address performance bottlenecks. * Work closely with researchers, conduct MLSys research to create new techniques, infrastructure, and tooling around emerging research capabilities.
Senior Research Scientist, Industrial Robotics Group
US, WA, Seattle
Amazon is seeking exceptional science talent to develop AI and machine learning systems that will enable the next generation of advanced manufacturing capabilities at unprecedented scale. We're building revolutionary software infrastructure that combines cutting-edge AI, large-scale optimization, and advanced manufacturing processes to create adaptive production control systems. As a Senior Research Scientist, you will develop and improve machine learning systems that enable real-time manufacturing flow decisions. You will leverage state-of-the-art optimization and ML techniques, evaluate them against representative manufacturing scenarios, and adapt them to meet the robustness, reliability, and performance needs of production environments. You will invent new algorithms where gaps exist. You'll collaborate closely with software engineering, manufacturing engineering, robotics simulation, and operations teams, and your outputs will directly power the systems that determine what to build next, where to allocate resources, and how to maximize throughput. The ideal candidate brings deep expertise in optimization and machine learning, with a proven track record of delivering scientifically complex solutions into production. You are hands-on, writing significant portions of critical-path scientific code while driving your team's scientific agenda. If you're passionate about inventing the intelligent manufacturing systems of tomorrow rather than optimizing those of today, this role offers the chance to make a lasting impact on the future of automation. Key job responsibilities - Identify and devise new scientific approaches for constraint identification, dispatch optimization, WIP release control, and predictive flow intelligence when the problem is ill-defined and new methodologies need to be invented - Lead the design, implementation, and successful delivery of scientifically complex solutions for real-time manufacturing flow optimization in production - Design and build ML models and optimization algorithms including constraint prediction, starvation risk forecasting, and dispatch optimization - Write a significant portion of critical-path scientific code with solutions that are inventive, maintainable, scalable, and extensible - Execute rapid, rigorous experimentation with reproducible results, closing the gap between simulation and real manufacturing environments - Build evaluation benchmarks that measure model performance against manufacturing outcomes including constraint utilization and throughput rather than traditional ML metrics alone - Influence your team's science and business strategy through insightful contributions to roadmaps, goals, and priorities - Partner with manufacturing engineering, robotics simulation, and applied intelligence teams to ensure scientific approaches are grounded in operational reality - Drive your team's scientific agenda and role model publishing of research results at peer-reviewed venues when appropriate and not precluded by business considerations - Actively participate in hiring and mentor other scientists, improving their skills and ability to deliver - Write clear narratives and documentation describing scientific solutions and design choices
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