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
Sr. Applied Scientist, Prime Video - Title Lifecycle Presentation
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! The Prime Video Title Lifecycle Presentation team sits at the intersection of science, experimentation, and customer experience. We leverage data signals and rigorous testing to present the most engaging information about our content to customers at precisely the right moment. Our mission is to ensure every customer interaction with Prime Video content is informed, relevant, and compelling in order to drive discovery and engagement across our vast catalog. We're seeking a Sr. Applied Scientist who excels at building sophisticated machine learning systems for content presentation and discovery. The ideal candidate brings deep expertise in: - Multi-modal embeddings for rich metadata representation, enabling nuanced understanding of content attributes and customer preferences - Contextualized ranking systems that adapt to customer intent, viewing context, and real-time signals - Reinforcement learning frameworks that create continuous improvement loops, allowing our systems to learn and optimize from customer interactions over time - General modeling techniques with strong fundamentals in machine learning and statistical methods - Recommender systems experience, with proven ability to build and scale personalization solutions You'll work with technology to solve complex problems in content discovery, leveraging large-scale data to create experiences that delight millions of Prime Video customers worldwide. Key job responsibilities - Lead Cross-Functional Science Initiatives: Drive a diverse portfolio of applied science projects spanning recommender systems, generative AI agent development and evaluation across multiple modalities, and computer vision applications. Demonstrate both breadth of understanding across technical domains and sufficient depth in each area to effectively lead multiple concurrent initiatives to successful outcomes. - Bridge Science and Engineering for Production-Scale Deployment: Partner with engineering teams to productionize machine learning models at Prime Video scale. Develop production-ready science code that meets engineering standards for performance, reliability, and maintainability, ensuring seamless transition from research to deployment. - Mentor and Develop Technical Talent: Provide technical mentorship and guidance to junior scientists and engineers on applied science methodologies, best practices, and professional development. Foster a culture of scientific rigor and continuous learning within the team.
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, WW Sustainability
US, WA, Seattle
Join us at the forefront of Amazon's sustainability initiatives to work on environmental and social advancements that support Amazon's long-term worldwide sustainability strategy. At Amazon, we're working to be the most customer-centric company on earth. To get there, we need exceptionally talented, bright, and driven people. We are looking for a Research Scientist to join our growing Sustainability team to drive the science behind value chain decarbonization. This role will establish Amazon's scientific methodologies for sector- and cross-sectoral decarbonization mechanisms, and establish benchmarks for automated validation and risk assessment. As a Research Scientist, you will be responsible for independently leading assessments of environmental issues across the full spectrum of Amazon businesses and evaluating sustainability impacts across the value chain. You will independently develop quality frameworks and methodologies that enable Amazon to scale procurement of high-quality environmental interventions while maintaining scientific rigor and environmental integrity. Key job responsibilities Develop quality assessment frameworks for complex environmental interventions, baseline-setting approaches, and measurement methodologies Build quantitative benchmark and statistical models that enable scalable evaluation across heterogeneous data sources Create attribution methodologies for supply chain interventions across Amazon's diverse footprint Develop social and environmental safeguard criteria that integrate community impact assessments Collaborate with cross-functional teams including procurement, sustainability operations, and business units to translate scientific methodologies into operational requirements Work under the direction of senior business leaders while acting as lead Subject Matter Expert for value chain decarbonization science, including designing and leading research, data collection, modeling, documentation, interpretation, and validation 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.
Applied Scientist II, Alexa Ads
IN, KA, Bengaluru
Alexa+ is the world’s best Generative AI powered personal assistant / agent for consumers, and is becoming the conversational AI interface for Amazon services with the launch of Alexa for Shopping on Amazon.com and Amazon mobile app. At Alexa Ads, we are creating industry's first and most advanced Agentic Advertising products to drive Agentic Commerce. We are seeking an Applied Scientist to join our newly expanding team in India focused on Alexa Agentic/Conversational Ads and Personalization. In this role, you will build machine learning models that seamlessly and naturally integrate relevant advertising into the Alexa experience while deeply personalizing user interactions. You will work closely with other scientists, engineers, and product managers to take models from conception to production. Key job responsibilities - Design, develop, and evaluate innovative machine learning and deep learning models for natural language processing (NLP), recommendation systems, and personalization. - Conduct hands-on data analysis and build scalable ML pipelines. - Design and run A/B experiments to measure the impact of new models on customer experience and ad performance. - Collaborate with software development engineers to deploy models into high-scale, real-time production environments. About the team We are building a new science team in Bangalore to solve some of the most impactful problems in computational advertising. This isn't about tweaking existing models as we are rethinking how ads are ranked, priced, and personalized across voice-first and screen-first surfaces. These are problems that don't have textbook solutions. Key points to note about the team: 🧪 Greenfield team - you are not joining a mature org with rigid processes. You will shape the science roadmap, pick the problems, and define the culture from day one. 📈 Direct business impact — your models directly drive revenue. No yearly cycles to see if your work matters. 🌏 Global scope, local autonomy — collaborate with scientists and engineers across Seattle, Sunnyvale, and Bangalore, but own your problem space end-to-end. 🎓 Ship AND Publish: We encourage top-tier publications (NeurIPS, ACL, EMNLP, KDD, ICML, WWW) while ensuring your research hits production.
Applied Scientist, PXT Central Science
US, WA, Seattle
The People eXperience Technology (PXT) Central Science (PXTCS)'s mission is to make PXT the most scientific, technologically proficient, and inclusive HR organization in the world. PXTCS does this by accelerating scientific rigor in business-led initiatives, working backwards from employee experience, and delivering science-driven products that improve the well-being of and value of work for Amazonians worldwide. We are seeking an Applied Scientist to build production machine learning systems that solve complex business problems at scale. You will design, develop, and deploy ML solutions that directly impact millions of users and drive strategic decision-making across the organization. In this role, you will work on challenging problems spanning predictive modeling, computer vision, natural language processing, recommendation systems, and generative AI applications. You will collaborate with cross-functional teams to translate ambiguous business challenges into rigorous technical solutions. Key job responsibilities - Apply and adapt state-of-the-art scientific techniques to solve well-defined problems in employee experience, using reasonable assumptions, data, and customer requirements. - Design, develop, and implement small-to-medium ML components with input and guidance from senior scientists, taking ownership of the code in your components. - Write secure, stable, testable, maintainable, well-reviewed code (at the SDE I bar) to deliver solutions into production that benefit customers and the business. - Collaborate with cross-functional partners to understand business context and impact, and help mentor interns. - Communicate complex technical concepts to diverse audiences, from technical peers to senior leadership About the team The People eXperience and Technology Central Science Team (PXTCS) uses economics, applied science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal.
Sr Applied Scientist, WW Prime , WW Prime - AI/ML Science
US, WA, Seattle
Interested in modeling and understanding customer behavior through machine learning, artificial intelligence, and data mining over TB scale data with huge business impact on millions of customers? Join our team of Scientists developing models to model customer behavior and optimize the customer experience with Amazon Prime. This includes understanding who our customers are, long-term value of the Prime membership program, and creating the right personalized framework for content and subscription optimization. As an AI/ML expert, you will partner directly with product owners to intake, build, and directly apply your modeling solutions. There are numerous scientific and technical challenges you will get to tackle in this role, such as optimizing/fine-tuning GenAI/LLM solutions for Prime personalization, building GenAI foundation models, global scalability of models, combinatorial optimization, cold start problem, accelerated experimentation, short/long term goals modeling, and multi-step optimization leading to reinforcement learning of the customer journey. We employ techniques from GenAI/LLMs, supervised/semi-supervised learning, deep learning, transformer architectures, using outcomes from causal Econometric modeling, and Reinforcement learning. As the central science team within Prime, our expertise gets routinely called upon to weigh in on a variety of topics. We also emphasize the need and value of scientific research and have developed a strong publication and patent record (internally/externally) which you will be a part of. You will also utilize and be exposed to the latest in ML technologies and infrastructure: AWS technologies (EMR/Spark, Sagemaker, DynamoDB, S3, ClaudeCode), various AI/ML algorithms and techniques (Deep Learning, GenAI/LLMs, transformers, supervised/unsupervised/semi-supervised/reinforcement learning), and statistical modeling techniques. Stay abreast of current literature in the field and advance/build novel science solutions leveraging SoTA solutions. Build and develop AI/ML models and supporting infrastructure at TB scale, in coordination with software engineering teams. Leverage Deep Learning and GenAI solutions for building foundation models and personalized optimization solution. Develop offline policy estimation tools and integrate with measurement systems/econometric models. Establish scalable, efficient, automated processes for large scale data analyses, science development, science validation and model implementation. Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes. Work closely with the business to understand their problem space, identify the opportunities and formulate the problems. Use AI/machine learning, data mining, statistical techniques and others to create actionable, meaningful, and scalable solutions for the business problems. Design, develop and evaluate highly innovative models and statistical approaches to understand and predict customer behavior and to solve business problems. Key job responsibilities Stay abreast of current literature in the field and advance/build novel science solutions leveraging SoTA solutions. Build and develop AI/ML models and supporting infrastructure at TB scale, in coordination with software engineering teams. Leverage Deep Learning and GenAI solutions for building foundation models and personalized optimization solution. Develop offline policy estimation tools and integrate with measurement systems/econometric models. Establish scalable, efficient, automated processes for large scale data analyses, science development, science validation and model implementation. Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes. Work closely with the business to understand their problem space, identify the opportunities and formulate the problems. Use AI/machine learning, data mining, statistical techniques and others to create actionable, meaningful, and scalable solutions for the business problems. Design, develop and evaluate highly innovative models and statistical approaches to understand and predict customer behavior and to solve business problems.
Applied Scientist, International Seller Services
US, WA, Seattle
Are you fascinated by the power of Natural Language Processing (NLP) and Large Language Models (LLM) to transform the way we interact with technology? Are you passionate about applying advanced machine learning techniques to solve complex challenges in the e-commerce space? If so, Amazon's International Seller Services team has an exciting opportunity for you as an Applied Scientist. At Amazon, we strive to be Earth's most customer-centric company, where customers can find and discover anything they want to buy online. Our International Seller Services team plays a pivotal role in expanding the reach of our marketplace to sellers worldwide, ensuring customers have access to a vast selection of products. As an Applied Scientist, you will join a talented and collaborative team that is dedicated to driving innovation and delivering exceptional experiences for our customers and sellers. You will be part of a global team that is focused on acquiring new merchants from around the world to sell on Amazon’s global marketplaces around the world. The position is based in Seattle but will interact with global leaders and teams in Europe, Japan, China, Australia, and other regions. Join us at the Central Science Team of Amazon's International Seller Services and become part of a global team that is redefining the future of e-commerce. With access to vast amounts of data, emerging technology, and a diverse community of talented individuals, you will have the opportunity to make a meaningful impact on the way sellers engage with our platform and customers worldwide. Together, we will drive innovation, solve complex problems, and shape the future of e-commerce. Key job responsibilities Apply your expertise in LLM models to design, develop, and implement scalable machine learning solutions that address complex language-related challenges in the international seller services domain. Collaborate with cross-functional teams, including software engineers, data scientists, and product managers, to define project requirements, establish success metrics, and deliver high-quality solutions. Conduct thorough data analysis to gain insights, identify patterns, and drive actionable recommendations that enhance seller performance and customer experiences across various international marketplaces. Continuously explore and evaluate state-of-the-art NLP techniques and methodologies to improve the accuracy and efficiency of language-related systems. Communicate complex technical concepts effectively to both technical and non-technical stakeholders, providing clear explanations and guidance on proposed solutions and their potential impact. A day in the life Push the boundaries of applied science - fine-tune large language models and develop novel NLP techniques to crack complex challenges in seller acquisition, content generation, and catalog understanding Work with data at massive scale - tap into some of the richest e-commerce datasets in the world to uncover patterns, generate insights, and drive real business impact Turn research into reality - prototype bold ideas, then partner with engineers to bring your models into production, balancing scientific rigor with real-world scalability Think globally, deliver worldwide - collaborate with leaders and teams across Europe, Japan, China, and Australia to build solutions that generalize across international marketplaces Solve problems that matter - translate ambiguous business challenges into well-scoped science problems that directly serve sellers and customers around the globe Collaborate with the best - engage in design reviews, contribute to technical thought leadership, and learn from a diverse community of world-class scientists and engineers Never stop learning - stay at the frontier of NLP, LLMs, and applied ML, bringing the latest research advances into your work Own your impact - operate with a customer-obsessed mindset where every model you build helps sellers thrive and expands selection for customers worldwide
Sr. Communication Systems Research Scientist – Radio Resource Management
US, TX, Austin
Amazon Leo is an initiative to launch a constellation of Low Earth Orbit satellites providing low-latency, high-speed broadband connectivity to unserved and underserved communities around the world. As a Communication Systems Research Scientist, this role owns the research and system design of the radio resource management (RRM) and radio access layers of Amazon Leo’s direct-to-device (D2D) system, delivering 3GPP-compliant service to unmodified commercial handsets. The Role: Be part of the team defining the communication system and architecture of Amazon’s direct-to-device wireless network and analyzing its system level performance: beam and cell capacity, spectral efficiency, coverage, latency and service availability. This is a unique opportunity to innovate with few legacy constraints, in a segment where the standard itself is still being written. This role leads the research and system design of radio resource management (RRM) for a 3GPP Non-Terrestrial Network (NTN), where D2D upends terrestrial assumptions: a power-limited handset with a near-isotropic antenna, very large cells, hopping beams, large time-varying delay and Doppler, and scarce shared spectrum. RRM in time, frequency and spatial domains is the focus, but the role reasons across the stack, from L1/L2 up through RRC, NAS and 5GC interworking. Agentic AI is expected to be a standard part of the work for development, optimization, tests and debugging, with the scientist accountable for the algorithms, models and conclusions. 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. Key job responsibilities • Research, design and specify RRM algorithms for Amazon Leo’s 3GPP-based D2D system: MAC scheduling, link adaptation, power control, HARQ strategy, DRX, admission and congestion control, and load balancing, mapping 5QI and QoS flow requirements to scheduler behavior across voice, messaging, emergency and data services. • Treat beam management as part of joint resource optimization, not a standalone process, optimizing it with band assignment, packet scheduling and user pairing in multi-user MIMO (MU-MIMO). • Define the RRM framework for NTN conditions: earth-fixed and earth-moving cells, large time-varying propagation delay, ephemeris-assisted timing and Doppler pre-compensation, extended timing advance, selective HARQ feedback disabling, feeder link and satellite handovers, and interference and spectrum sharing across beams, satellites and terrestrial networks using the same MNO spectrum. • Design mobility and service continuity for a network where the base stations (i.e., satellites) move rather than the user: idle and connected mode mobility, location and time based conditional handover, cell reselection, paging, tracking area design, and NTN-to-terrestrial continuity. • Specify supporting L1/L2 elements with the PHY team: numerology under Doppler, PRACH and initial access, coverage enhancement through repetition, synchronization at low SNR, receiver abstraction, and FEC and BLER modeling for link adaptation. • Keep the radio design coherent with the networking layers: RRC and NAS, RLC and PDCP over long-RTT links, CU/DU split, NTN gateway and 5GC/EPC integration, and transport behavior. • Develop link-level and system-level simulators capturing constellation dynamics, beam patterns, handset characteristics, traffic models and RRM behavior, and use agentic AI across that loop: build and refactor simulation code, scale parameter sweeps, optimize scheduler and link adaptation parameters, explore configuration spaces too large to sweep by hand, maintain regression tests, and triage failures across logs, traces and over-the-air captures. • Translate research into system requirements and implementation-level specifications, and work with modem, payload, ground, RF, ASIC and Testbed teams through integration, field trials and link bring-up, root-causing gaps between simulation, implementation and over-the-air behavior in a fast-paced environment. • Represent Amazon Leo in 3GPP and other standards development organizations, develop and defend contributions on NTN and D2D work items, and contribute patents and publications.
Sr. Communication Systems Engineer
US, CA, San Diego
Amazon Leo is an initiative to launch a constellation of Low Earth Orbit satellites that will provide low-latency, high-speed broadband connectivity to unserved and underserved communities around the world. Come work at Amazon! The Role: Be part of the team defining the overall communication system and architecture of Leo’s broadband wireless network. This is a unique opportunity to innovate and define groundbreaking wireless technology with few legacy constraints. The team develops and designs the communication system of Leo and analyzes its overall system level performance such as for overall throughput, latency, system availability, packet loss etc. This role in particular will be responsible for leading the effort in integration, verification and testing of the systems especially focused on MAC and higher layer testing. This role will also be responsible developing and testing advanced L1/L2/L3 concept to improve the performance and reliability of the LEO network. This role will also be part of a team and develop simulation tools with particular emphasis on modeling the physical layer aspects such as advanced receiver modeling and abstraction, interference cancellation techniques, FEC abstraction models etc. In this role you will: - Work within a project team and take the responsibility for the Leo’s communication system design, system integration and verification. - Work as a part of the team in building a suite of system and network simulation services in Matlab / C++ / Python - Develop requirements from system level to HW/SW level and define test cases associated with the requirements. - Identify additional HW and SW that are needed for the purposes of verification and guide the HW/SW development team in the development of these test solutions/tools// - Work closely with implementation teams to simulate expected system level performance and provide quick feedback on potential improvements - Write scripts / code for functions / features required for specific simulation, testing and verification of given RF system EXPORT CONTROL REQUIREMENTS 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.
PhD Economics Intern – Structural IO, Summer 2027
US, WA, Seattle
Amazon Economics is seeking Structural IO Economist (STRUC) Interns who are passionate about applying structural econometric methods to solve real-world business challenges. STRUC economists specialize in the econometric analysis of models that involve the estimation of fundamental preferences and strategic effects. In this full-time internship (40 hours per week, with hourly compensation), you'll work with large-scale datasets to model strategic decision-making and inform business optimization, gaining hands-on experience that's directly applicable to dissertation writing and future career placement. By applying to this role, you are automatically being considered for all our available STRUC internships in 2027. Key job responsibilities As a STRUC Economist Intern, you'll specialize in structural econometric analysis to estimate fundamental preferences and strategic effects in complex business environments. Your responsibilities include: - Analyze large-scale datasets using structural econometric techniques to solve complex business challenges - Applying discrete choice models and methods, including logistic regression family models (such as BLP, nested logit) and models with alternative distributional assumptions - Utilizing advanced structural methods including dynamic models of customer or firm decisions over time, applied game theory (entry and exit of firms), auction models, and labor market models - Building datasets and performing data analysis at scale - Collaborating with economists, scientists, and business leaders to develop data-driven insights and strategic recommendations - Tackling diverse challenges including pricing analysis, competition modeling, strategic behavior estimation, contract design, and marketing strategy optimization - Helping business partners formalize and estimate business objectives to drive optimal decision-making and customer value - Build and refine comprehensive datasets for in-depth structural economic analysis - Present complex analytical findings to business leaders and stakeholders
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