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
Data Scientist III, Amazon 1P Credito, Payments
BR, SP, Sao Paulo
Do you feel the challenge and the adrenaline kick when a huge data-set stares you in the face and you know that somewhere inside are hidden very important business insights that can fundamentally alter the way top business leaders think and act? Do you enjoy presenting strong data backed insights to business leaders; insights that can topple their long held beliefs and compel them to change their direction completely? If yes, then you are the one we are looking for. We are looking to invite passionate leaders, with expertise in generate power business insights from very large datasets, on a journey where the primary aim would be to enable needle moving business impacts through statistical analysis. We are looking for leaders who can envision the design and development of analytical infrastructure which can support strategic and tactical decision-making. Those who join this high visibility team would have to navigate through significant ambiguity in defining business problems and converting them to analytical problems. This role requires additional exposure and experience to Machine Learning. Key job responsibilities Use machine learning and analytical techniques to create scalable solutions for business problems • Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes • Design, development, evaluate and deploy innovative and highly scalable ml models such as risk scorecards, income models, fraud models for predictive learning in credit risk applications • Research and implement novel machine learning and statistical approaches • Work closely with software engineering teams to drive real-time model implementations and new feature creations • Work closely with business owners and operations staff to optimize various business operations • Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation • Mentor other scientists and engineers in the use of ML techniques • Innovate with the latest GenAI technology to build highly automated solutions for efficient customer promotions • Design, develop and deploy end-to-end machine learning solutions in the Amazon production environment to delight Amazon customers • Collaborate with cross-functional teams to develop comprehensive ML/statistical models that can scale to millions of customers to multiple countries Understand the credit risk data and evaluate the best ml model/ solution for dynamic business problems. About the team Brazil Payments is part of the International Emerging Stores Payments team and focuses on supporting the launch of new payment and financial products to our customers in Brazil.
Data Scientist, Amazon Ads Marketing Decision Science
US, NY, New York
Amazon Advertising drives billions of ad impressions and millions of clicks daily, powering discovery and sales for advertisers across Amazon's Retail and Marketplace businesses. The Ads Marketing Decision Science team sits at the intersection of data science and marketing strategy. We build intelligent, data-driven systems that analyze advertiser behavior at large scale to deliver the right guidance to the right advertiser at the right time. Our work spans behavioral modeling, content intelligence, automated decision systems, and GenAI applications, enabling personalized marketing experiences that help advertisers make smarter advertising decisions and grow their business on Amazon. We are looking for a Data Scientist who brings strong fundamentals in machine learning, causal inference, and statistical modeling to solve real advertiser problems. You will build predictive models, design experiments, develop segmentation frameworks, and leverage GenAI capabilities where applicable, taking solutions end-to-end from proof-of-concept to production at scale. You will partner closely with scientists, engineers, and product managers on a daily basis to prototype rapidly, ensure data integrity in production systems, and deliver measurable advertiser impact. If you are passionate about solving real-world problems with next level science, come join us as we innovate and make history. Key job responsibilities • Define and execute data science solutions end-to-end, from problem framing through production deployment. • Build machine learning models (classification, regression, clustering, ranking) for advertiser segmentation, propensity modeling, and recommendations. • Apply causal inference and experimentation methods (A/B testing, difference-in-differences, propensity score matching) to measure the impact of marketing interventions. • Analyze large-scale advertiser behavioral data to identify trends, surface growth opportunities, and support optimal decision making. • Collaborate with colleagues across science and engineering disciplines for fast turnaround proof-of-concept prototyping at scale. • Establish and drive data hygiene best practices to ensure coherence and integrity of data feeding into production ML/AI solutions. • Leverage GenAI and LLM capabilities to enhance science products where applicable A day in the life You will solve real-world problems by analyzing large volumes of advertiser data, building predictive models, designing experiments, and measuring business impact. You will prototype rapidly, validate ideas with data, and partner with engineers to productize and scale successful solutions. You will collaborate daily with scientists, engineers, and product managers across the advertising organization, working in a cross-functional, fast-paced environment where data drives decisions and helps advertisers grow. About the team We are a team of Applied Scientists, Research Scientists, Data Scientists, and Business Intelligence Engineers with deep expertise in ML, NLP, Gen-AI, RL, and causal inference, from a diverse range of backgrounds. We partner closely with strong engineers, product managers, and sales leaders who bring ads-industry depth and experience building scalable modeling and software solutions.
2027 Applied Scientist Internship – PhD, Amazon University Talent Acquisition
GB, London
We're building systems that turn research into real-world impact — ensuring flawless streaming for millions of Prime Video customers, shaping the future of AI-driven shopping with Rufus, advancing speech generation and conversational AI, optimizing large-scale infrastructure through intelligent observability, and transforming how people and jobs find each other. If this sounds interesting to you then we have a range of opportunities for you to explore. We're looking for PhD students across multiple research domains to invent, design, and implement state-of-the-art solutions for never-before-solved problems. Your work here won't just stay in a notebook — it ships to production and reaches customers worldwide. Check out the details below including the job responsibilities, team details, and basic qualifications before submitting your application. You can find more information about the Amazon Science community as well as interview preparation tips via the links below; - https://www.amazon.science/ - https://amazon.jobs/content/en/career-programs/university/science - https://amazon.jobs/content/en/how-we-hire/university-roles/applied-science Key job responsibilities As an Applied Science Intern, you will own the design and development of end-to-end systems. You'll have the opportunity to write technical white papers, create roadmaps and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. You will have the opportunity to design new algorithms, models, or other technical solutions whilst experiencing Amazon's customer focused culture. The ideal intern should have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A day in the life You'll spend your first weeks scoping your project with your mentor, then own the research and implementation end-to-end. Your work could involve building computer vision models that detect quality issues across Prime Video's content library, developing multimodal AI solutions that power Amazon's shopping assistant Rufus, creating automated reasoning tools that verify distributed systems at scale, engineering intelligent observability frameworks for large-scale infrastructure, or advancing recommendation models that connect people with the right jobs — depending on the team you're matched with. Many interns publish at top-tier conferences or see their work deployed to production before the internship ends. Interns may also be considered for a return offer at the end of their internship, subject to performance evaluation and headcount availability. Further benefits of an Amazon Science internship include; - All of our internships offer a competitive salary - Interns are paired with an experienced manager and mentor(s) - Interns get invited to different intern program or office events - Interns can build their professional and personal network with other Amazon Scientists - Interns can potentially publish work at top tier conferences About the team We're hiring interns for multiple teams in the UK, including but not limited to; • Prime Video Video Quality Analysis – Develops AI and machine learning solutions using computer vision, audio processing, and generative AI to detect and prevent streaming quality issues across Prime Video's vast content library • Rufus Features Science UK – Shapes AI-driven shopping experiences at Amazon, working on projects from enabling Rufus to take actions on behalf of customers to generating multimodal answers combining text, image, audio, and video. • READI – Observability, Triage & Peak Readiness – Builds intelligent log analytics and automated performance frameworks that transform system telemetry into actionable insights for large-scale distributed systems. • Automated Reasoning Group – Ensures program and systems correctness through deductive proof, model checking, formal verification, and runtime conformance monitoring for large-scale distributed systems. You'll submit a single application and we'll match you with science teams best aligned with your research interests. Applications are reviewed on a rolling basis, and your application stays active until we find a team match or confirm there are no matches available. Start dates are available throughout the year for durations of between 3–6 months. Please note, each team has different start date and duration preferences — your recruiter will confirm the preferences of the team you're matched with prior to interviewing. We offer science internships in multiple locations across the EMEA region and you can indicate your interest in all these locations by applying here (Austria, Estonia, France, Germany, Ireland, Israel, Italy, Jordan, Luxembourg, Netherlands, Poland, Romania, South Africa, Spain, Sweden, UAE, and UK). Please note we do not offer remote internships.
2027 Applied Scientist Internship – PhD, Amazon University Talent Acquisition
IL, Tel Aviv
We're building systems that turn research into real-world impact — powering sports experiences for millions of Prime Video customers, pioneering multimodal document intelligence, building autonomous AI agents that reason, plan, and act, and transforming how customers discover products they love. If this sounds interesting to you then we have a range of opportunities for you to explore. We're looking for PhD students across multiple research domains to invent, design, and implement state-of-the-art solutions for never-before-solved problems. Your work here won't just stay in a notebook — it ships to production and reaches customers worldwide. Check out the details below including the job responsibilities, team details, and basic qualifications before submitting your application. You can find more information about the Amazon Science community as well as interview preparation tips via the links below; - https://www.amazon.science/ - https://amazon.jobs/content/en/career-programs/university/science - https://amazon.jobs/content/en/how-we-hire/university-roles/applied-science Key job responsibilities As an Applied Science Intern, you will own the design and development of end-to-end systems. You'll have the opportunity to write technical white papers, create roadmaps and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. You will have the opportunity to design new algorithms, models, or other technical solutions whilst experiencing Amazon's customer focused culture. The ideal intern should have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A day in the life You'll spend your first weeks scoping your project with your mentor, then own the research and implementation end-to-end. Your work could involve building computer vision models that power live sports experiences for Prime Video, developing multimodal GenAI solutions for AWS document intelligence, creating agentic AI systems that reason and act autonomously, or advancing recommendation models that transform how customers discover content — depending on the team you're matched with. Many interns publish at top-tier conferences or see their work deployed to production before the internship ends. Interns may also be considered for a return offer at the end of their internship, subject to performance evaluation and headcount availability. Further benefits of an Amazon Science internship include; - All of our internships offer a competitive salary - Interns are paired with an experienced manager and mentor(s) - Interns get invited to different intern program or office events - Interns can build their professional and personal network with other Amazon Scientists - Interns can potentially publish work at top tier conferences About the team We're hiring interns for multiple teams in Israel, including but not limited to; • Prime Video Sports — Build innovative sports experiences for Prime Video, spanning computer vision, 3D simulation, and personalized content recommendations. • Personalization — Leverage LLMs, NLP, and recommender systems to match customers with products that align with their passions and shopping preferences. • Agentic AI — Build next-generation agentic AI systems that automate real-world knowledge work, spanning retrieval-augmented generation, multi-agent workflows, long-term memory and personalization, knowledge-graph construction, and agent evaluation. • DS3 Textract — Develop multimodal generative AI algorithms that pioneer state-of-the-art document understanding solutions impacting millions of customers. You'll submit a single application and we'll match you with science teams best aligned with your research interests. Applications are reviewed on a rolling basis, and your application stays active until we find a team match or confirm there are no matches available. Start dates are available throughout the year. Some teams offer full-time internships (3–6 months) while others offer part-time positions (50–60%, 8–12 months) — your recruiter will confirm the format during team matching. We offer science internships in multiple locations across the EMEA region and you can indicate your interest in all these locations by applying here (Austria, Estonia, France, Germany, Ireland, Israel, Italy, Jordan, Luxembourg, Netherlands, Poland, Romania, South Africa, Spain, Sweden, UAE, and UK). Please note we do not offer remote internships.
2027 Applied Scientist Internship – PhD, Amazon University Talent Acquisition
ES, Madrid
We're building the intelligence behind how customers discover, trust and enjoy products on Amazon. We're solving complex catalogue quality challenges with machine learning, enhancing product discovery through computer vision and multimodal AI and pioneering agentic systems that autonomously navigate and stress-test the Amazon shopping experience to surface insights at scale. We're looking for PhD students across multiple research domains to invent, design, and implement state of the art solutions for never before solved problems. Your work here won't just stay in a notebook, it ships to production and reaches customers worldwide. Check out the details below including the job responsibilities, team details, and basic qualifications before submitting your application. You can find more information about the Amazon Science community as well as interview preparation tips via the links below; - https://www.amazon.science/ - https://amazon.jobs/content/en/career-programs/university/science - https://amazon.jobs/content/en/how-we-hire/university-roles/applied-science Key job responsibilities As an Applied Science Intern, you will own the design and development of end-to-end systems. You'll have the opportunity to write technical white papers, create roadmaps and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. You will have the opportunity to design new algorithms, models, or other technical solutions whilst experiencing Amazon's customer focused culture. The ideal intern should have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A day in the life You'll spend your first weeks scoping your project with your mentor, then own the research and implementation end-to-end. Your work could involve developing machine learning and data analysis solutions that detect and resolve catalogue quality issues at massive scale, building computer vision and multimodal learning models that transform how customers discover and interact with products, engineering universal ML systems that make shopping on Amazon easier and more visually delightful, or creating autonomous agentic shoppers that tirelessly navigate the Amazon website to provide feedback and actionable insights — depending on the team you're matched with. Many interns publish at top-tier conferences or see their work deployed to production before the internship ends. Interns may also be considered for a return offer at the end of their internship, subject to performance evaluation and headcount availability. Further benefits of an Amazon Science internship include; - All of our internships offer a competitive salary - Interns are paired with an experienced manager and mentor(s) - Interns get invited to different intern program or office events - Interns can build their professional and personal network with other Amazon Scientists - Interns can potentially publish work at top tier conferences About the team We're hiring interns for multiple teams in Spain including but not limited to; •Tamale - Using Machine Learning and Data analysis solutions to solve complex catalogue quality problems • NintAI- Developing AI solutions, focusing on computer vision and multimodal learning to enhance how customers discover and interact with products • Home Innovation tech- Building universal, state of the art Machine Learning technology that makes shopping on Amazon easier and more visually delightful for our customers • EU Intech- Pioneers a population of agentic shoppers, autonomous AI agents, that tirelessly navigate and shop on the Amazon website, providing feedback and insights to improve the customer experience You'll submit a single application and we'll match you with science teams best aligned with your research interests. Applications are reviewed on a rolling basis, and your application stays active until we find a team match or confirm there are no matches available. Start dates are available throughout the year for durations of between 3–6 months. Please note, each team has different start date and duration preferences — your recruiter will confirm the preferences of the team you're matched with prior to interviewing. We offer science internships in multiple locations across the EMEA region and you can indicate your interest in all these locations by applying here (Austria, Estonia, France, Germany, Ireland, Israel, Italy, Jordan, Luxembourg, Netherlands, Poland, Romania, South Africa, Spain, Sweden, UAE, and UK). Please note we do not offer remote internships.
Senior Data Scientist, AWS Central Econ and Science
US, NY, New York
Our team, AWS Central Econ and Science, partners across AWS leveraging data, economics, science, and business context to build new tech, tools and policies that help AWS customers and the business. In this role you will help build out AWS's CLV framework in support of direct, partner and marketplace selling motions. This includes end to end ownership of notification for human and agentic selling motions to improve customer value from AWS products. Key job responsibilities Ownership includes developing closed loop causal measurement systems along with explainability layers. We work backward through partnering deeply with our business partners to improve processes in addition to science products. We want this role to shape the direction of our efforts to drive value of AWS customers. A day in the life Our team takes big swings and works on hard cross organizational problems where the optimal success rate is not 100%. We ask people to grow their skills and stretch and do so in a supportive and fun environment. It’s about empirically measured impact, advancement, and fun on our team. We work hard during work hours but we also don’t encourage working at nights or on weekends except in very rare, high stakes cases. Burn out isn’t a successful long run strategy. Because we invest in the long run success of our group it’s important to have hobbies, relax and then come to work refreshed and excited. It makes for bigger impact, faster skill accrual and thus career advancement. About the team Our group is technically rigorous and encourages ongoing academic conference participation and publication. Our leaders are here for you and to enable you to be successful. We believe in being servant leaders focused on influence: good data work has little value if it doesn’t translate into actionable insights that are rolled out and impact the real economy. We are communication centric since being able to explain what we do ensures high success rates and lowers administrative churn. Also: we laugh a lot. If it’s not fun, what’s the point?
Senior Applied Scientist, ASCS AI Lab Team
US, WA, Seattle
We are seeking a Senior Applied Scientist to join our team in developing pioneering AI research, Generative AI, Agentic AI, Large Language Models (LLMs), Diffusion and Flow Models, and other advanced Machine Learning and Deep Learning solutions for Amazon Selection and Catalog Systems, within the AI Lab Team. This role offers a unique opportunity to work on AI research and AI products that will shape the future of online shopping experiences. Our team operates at the forefront of AI research and development, working on challenges that directly impact millions of customers worldwide. We push the boundaries of AI at both the foundational and application layers. As a Senior Applied Scientist, you will have the chance to experiment with LLMs and deep learning techniques, apply your research to solve real-world problems at an unprecedented scale, and collaborate with experienced scientists to contribute to Amazon's scientific innovation. Join us in redefining the future of shopping. Your work will directly influence how customers interact with the world's largest online store. Key job responsibilities - Design and implement novel AI solutions for Amazon catalog of products - Develop and train state-of-the-art LLMs, Diffusion Models, and other Generative AI models - Build and deploy autonomous AI Agents in Amazon production ecosystem - Scale AI models to handle billions of diverse products across multiple languages and geographies - Conduct research in areas such as Autonomous AI Agents, Generative AI, Language Modeling, Multi-modality Computer Vision, Diffusion Models, Reinforcement Learning - Collaborate with cross-functional teams to integrate AI models into Amazon's production ecosystem - Contribute to the scientific community through publications and conference presentations
Applied Scientist, Fauna
US, CA, Sunnyvale
We are seeking an Applied Scientist to focus on Robot Navigation. In this role, you'll research and develop advanced navigation systems that enable robots to move reliably and safely through complex, dynamic environments. You'll work across a broad spectrum of navigation approaches—from classical methods to learning-based techniques and foundation models—to build robust solutions for autonomous robot navigation. Key job responsibilities - Develop and implement robust navigation systems that enable reliable autonomous operation in complex, dynamic indoor environments with static and dynamic obstacles - Build simulation-based and on-device evaluation frameworks with comprehensive benchmarks and metrics for systematic comparison of navigation methods - Conduct sim-to-real transfer experiments, analyzing performance gaps and developing techniques to ensure reliable real-world navigation performance - Collaborate with world model, manipulation, and other teams to ensure seamless integration of navigation capabilities into the full robot system - Stay current with the latest advances in robot navigation, spatial reasoning, and related fields, and apply relevant findings to improve system performance - Mentor fellow scientists and engineers while maintaining strong individual technical contributions About the team Fauna Robotics, an Amazon company, is building capable, safe, and genuinely delightful robots for everyday life. Our goal is simple: make robots people actually want to live and interact with in everyday human spaces. We believe that future won’t arrive until building for robotics becomes far more accessible. Today, too much effort is spent reinventing the fundamentals. We’re changing that by developing tightly integrated hardware and software systems that make it faster, safer, and more intuitive to create real-world robotic products.
Sr Applied Scientist, Ring AI
US, CA, Sunnyvale
Are you a passionate scientist who wants to build AI agents that make a real difference in people's lives? At Ring, our mission is to make neighborhoods safer, and we believe agentic AI will change how customers interact with their homes and communities. You'll invent agents that reason about real-world situations, take meaningful action, and keep customers in control, and then you'll see them reach millions of households. As an Applied Scientist, you'll work with talented peers to push the frontier of agentic AI. You'll build agents that turn the multimodal signals captured by Ring devices into understanding and action. You'll tackle open problems in planning, tool use, learning from feedback, and reliability, taking ideas from research all the way to deployment at scale. You'll collaborate with teams across Amazon to advance the science of customer experiences through highly optimized, integrated hardware and software platforms. Key job responsibilities - Design, develop, and deploy LLM-based agents that plan and carry out multi-step tasks for customers using tools, services, and device data. - Advance the state of the art in agent capabilities such as planning, tool use, memory, and learning from feedback (e.g., RL and agent fine-tuning), and publish where appropriate. - Partner with engineering, product, and science teams to turn research into agent-driven experiences that help keep homes and neighborhoods safer.
Sr. Applied Scientist, AI & AGI Security
US, NY, New York
We are seeking a Senior Applied Scientist to lead research and development of novel security validation and monitoring techniques for AI systems at scale. You will own and contribute to four critical workstreams: 1. Real-Time Agent Monitoring Design and implement scientific approaches for continuous behavioral analysis of AI agents in production—detecting anomalous actions, prompt injection exploitation, and policy violations in real time. 2. MCP Server Validation Develop novel validation frameworks to assess the security posture of Model Context Protocol (MCP) servers, including input sanitization verification, tool-use authorization boundaries, and data exfiltration detection. 3. AI-Enabled Application Validation Invent and deliver scalable methodologies for security testing of AI-enabled applications, including adversarial robustness evaluation, safety guardrail bypass detection, and trust boundary verification. 4. AI Asset Discovery & Inventory Research and build scalable techniques to automatically discover, identify, and catalog all AI-enabled applications and services across the company—maintaining a comprehensive, continuously updated database of AI assets. Key job responsibilities Invent • Identify and frame new research challenges in AI security where problems are ill-defined and require novel scientific paradigms at the product level. • Drive the team's scientific agenda for agent monitoring, validation research, and AI asset discovery; propose new initiatives and secure leadership buy-in. • Publish research results at peer-reviewed internal and external venues (e.g., USENIX Security, IEEE S&P, NeurIPS, ICML security workshops) when appropriate. • Articulate key scientific challenges of current and future AI security threats and present interventions to address them. • Make trade-offs between short-term tactical security needs and long-term research investments. Implement • Lead the design, implementation, and successful delivery of scientifically complex security solutions into production—both brand new systems and evolutions of existing ones. • Write significant portions of critical-path code for detection models, validation engines, and asset discovery / classification systems. • Independently assess and select appropriate technologies (e.g., streaming inference frameworks, graph-based anomaly detection, NLP-based service classification, code/traffic analysis for AI fingerprinting) for production systems. • Drive adoption of best practices in scientific methodology and software engineering across the team; provide insightful peer reviews of code, design, and architecture artifacts. • Deliver solutions that are inventive, maintainable, scalable, and extensible. Influence • Autonomously drive discussions with security engineers, product managers, and scientist peers across multiple teams. • Build consensus on larger cross-team security initiatives and factor complex efforts into independent workstreams. • Proactively identify and resolve endemic problems, including areas where current security tooling limits innovation of partner teams. • Actively recruit, mentor, and develop other scientists; provide technical assessments for promotions. • Contribute to the broader internal and external scientific communities as a subject matter expert in AI security. About the team Diverse Experiences Amazon Security 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. Why Amazon Security? At Amazon, security is central to maintaining customer trust and delivering delightful customer experiences. Our organization is responsible for creating and maintaining a high bar for security across all of Amazon’s products and services. We offer talented security professionals the chance to accelerate their careers with opportunities to build experience in a wide variety of areas including cloud, devices, retail, entertainment, healthcare, operations, and physical stores. Inclusive Team Culture In Amazon Security, it’s in our nature to learn and be curious. Ongoing DEI events and learning experiences inspire us to continue learning and to embrace our uniqueness. Addressing the toughest security challenges requires that we seek out and celebrate a diversity of ideas, perspectives, and voices. Training & 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, training, and other career-advancing resources here to help you develop into a better-rounded professional. Work/Life Balance We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why flexible work hours and arrangements are part of our culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve.
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