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
Senior Applied Scientist, Insights, Prime Video
GB, London
Come build the future of entertainment with us. Are you interested in shaping the future of movies and television? Do you want to define the next generation of how and what Amazon customers are watching? Prime Video is a premium streaming service that offers customers a vast collection of TV shows and movies - all with the ease of finding what they love to watch in one place. We offer customers thousands of popular movies and TV shows including Amazon Originals and exclusive licensed content to exciting live sports events. We also offer our members the opportunity to subscribe to add-on channels which they can cancel at anytime and to rent or buy new release movies and TV box sets on the Prime Video Store. Prime Video is a fast-paced, growth business - available in over 200 countries and territories worldwide. The team works in a dynamic environment where innovating on behalf of our customers is at the heart of everything we do. If this sounds exciting to you, please read on. The Insights team is looking for an Applied Scientist for our London office experienced in generative AI and large models. This is a wide impact role working with development teams across the UK, India, and the US. This greenfield project will deliver features that reduce the operational load for internal Prime Video builders and for this, you will need to develop personalized recommendations for their services. You will have strong technical ability, excellent teamwork and communication skills, and a strong motivation to deliver customer value from your research. Our position offers opportunities to grow your technical and non-technical skills and make a global impact immediately. Key job responsibilities - Develop machine learning algorithms for high-scale recommendations problems - Rapidly design, prototype and test many possible hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgement - Collaborate with software engineers to integrate successful experimental results into Prime Video wide processes - Communicate results and insights to both technical and non-technical audiences, including through presentations and written reports A day in the life You will lead the design of machine learning models that scale to very large quantities of data across multiple dimensions. You will embody scientific rigor, designing and executing experiments to demonstrate the technical effectiveness and business value of your methods. You will work alongside other scientists and engineering teams to deliver your research into production systems. About the team Our team owns Prime Video observability features for development teams. We consume PBs of data daily which feed into multiple observability features focussed on reducing the customer impact time.
Applied Scientist II, Last Mile Science
IN, KA, Bengaluru
Have you ever ordered a product on Amazon and when that box with the smile arrived you wondered how it got to you so fast? Have you wondered where it came from and how much it cost Amazon to deliver it to you? If so, the WW Amazon Logistics, Business Analytics team is for you. We manage the delivery of tens of millions of products every week to Amazon’s customers, achieving on-time delivery in a cost-effective manner. We are looking for an enthusiastic, customer obsessed, Applied Scientist with good analytical skills to help manage projects and operations, implement scheduling solutions, improve metrics, and develop scalable processes and tools. The primary role of an Operations Research Scientist within Amazon is to address business challenges through building a compelling case, and using data to influence change across the organization. This individual will be given responsibility on their first day to own those business challenges and the autonomy to think strategically and make data driven decisions. Decisions and tools made in this role will have significant impact to the customer experience, as it will have a major impact on how the final phase of delivery is done at Amazon. Ideal candidates will be a high potential, strategic and analytic graduate with a PhD in (Operations Research, Statistics, Engineering, and Supply Chain) ready for challenging opportunities in the core of our world class operations space. Great candidates have a history of operations research, and the ability to use data and research to make changes. This role requires robust program management skills and research science skills in order to act on research outcomes. This individual will need to be able to work with a team, but also be comfortable making decisions independently, in what is often times an ambiguous environment. Responsibilities may include: - Develop input and assumptions based preexisting models to estimate the costs and savings opportunities associated with varying levels of network growth and operations - Creating metrics to measure business performance, identify root causes and trends, and prescribe action plans - Managing multiple projects simultaneously - Working with technology teams and product managers to develop new tools and systems to support the growth of the business - Communicating with and supporting various internal stakeholders and external audiences
Applied Science Manager, Ads Measurement Science
US, NY, New York
The Measurement Intelligence Science Team (MIST) in the Measurement, Ad Tech, and Data Science (MADS) organization of Amazon Ads serves a centralized role developing solutions for a multitude of performance measurement products. We create solutions which measure the comprehensive impact of their ad spend, including sales impacts both online and offline and across timescales, and provide actionable insights that enable our advertisers to optimize their media portfolios. We leverage a host of scientific technologies to accomplish this mission, including Generative AI, classical ML, Causal Inference, Natural Language Processing, and Computer Vision. As an Applied Science Manager on the team, you will lead a team of scientists to define and execute a transformative vision for holistic measurement and reporting insights for ad effectiveness. Your team will own the science solutions for foundational experimentation platforms, foundational customer journey understanding technologies, state of the art attribution algorithms to measure the role of advertising in driving observed retail outcomes, and/or agentic AI solutions that help advertisers get quick access to custom insights that inform how to get the most out of their ad spend. Key job responsibilities You independently manage a team of scientists. You identify the needs of your team and effectively grow, hire, and promote scientists to maintain a high-performing team. You have a broad understanding of scientific techniques, several of which may fall out of your specific job function. You define the strategic vision for your team. You establish a roadmap and successfully deliver scientific solutions that execute that vision. You define clear goals for your team and effectively prioritize, balancing short-term needs and long-term value. You establish clear and effective metrics and scientific process to enforce consistent, high-quality artifact delivery. You proactively identify risks and bring them to the attention of your manager, customers, and stakeholders with plans for mitigation before they become roadblocks. You know when to escalate. You communicate ideas effectively, both verbally and in writing, to all types of audiences. You author strategic documentation for your team. You communicate issues and options with leaders in such a way that facilitates understanding and that leads to a decision. You work successfully with customers, leaders, and engineering teams. You foster a constructive dialogue, harmonize discordant views, and lead the resolution of contentious issues. About the team We are a team of scientists across Applied, Research, Data Science and Economist disciplines. You will work with colleagues with deep expertise in ML, NLP, CV, Gen AI, and Causal Inference with a diverse range of backgrounds. We partner closely with top-notch engineers, product managers, sales leaders, and other scientists with expertise in the ads industry and on building scalable modeling and software solutions.
Applied Science Manager, Ads Measurement Science
US, NY, New York
The Measurement Intelligence Science Team (MIST) in the Measurement, Ad Tech, and Data Science (MADS) organization of Amazon Ads serves a centralized role developing solutions for a multitude of performance measurement products. We create solutions which measure the comprehensive impact of their ad spend, including sales impacts both online and offline and across timescales, and provide actionable insights that enable our advertisers to optimize their media portfolios. We leverage a host of scientific technologies to accomplish this mission, including Generative AI, classical ML, Causal Inference, Natural Language Processing, and Computer Vision. As an Applied Science Manager on the team, you will lead a team of scientists to define and execute a transformative vision for holistic measurement and reporting insights for ad effectiveness. Your team will own the science solutions for foundational experimentation platforms, foundational customer journey understanding technologies, state of the art attribution algorithms to measure the role of advertising in driving observed retail outcomes, and/or agentic AI solutions that help advertisers get quick access to custom insights that inform how to get the most out of their ad spend. Key job responsibilities You independently manage a team of scientists. You identify the needs of your team and effectively grow, hire, and promote scientists to maintain a high-performing team. You have a broad understanding of scientific techniques, several of which may fall out of your specific job function. You define the strategic vision for your team. You establish a roadmap and successfully deliver scientific solutions that execute that vision. You define clear goals for your team and effectively prioritize, balancing short-term needs and long-term value. You establish clear and effective metrics and scientific process to enforce consistent, high-quality artifact delivery. You proactively identify risks and bring them to the attention of your manager, customers, and stakeholders with plans for mitigation before they become roadblocks. You know when to escalate. You communicate ideas effectively, both verbally and in writing, to all types of audiences. You author strategic documentation for your team. You communicate issues and options with leaders in such a way that facilitates understanding and that leads to a decision. You work successfully with customers, leaders, and engineering teams. You foster a constructive dialogue, harmonize discordant views, and lead the resolution of contentious issues. About the team We are a team of scientists across Applied, Research, Data Science and Economist disciplines. You will work with colleagues with deep expertise in ML, NLP, CV, Gen AI, and Causal Inference with a diverse range of backgrounds. We partner closely with top-notch engineers, product managers, sales leaders, and other scientists with expertise in the ads industry and on building scalable modeling and software solutions.
Senior Manager, Research Science, WW Stores Finance, WW Stores Finance
US, WA, Seattle
This role leads the science function in WW Stores Finance as part of the IPAT organization (Insights, Planning, Analytics and Technology), driving transformative innovations in financial analytics through AI and machine learning across the global Stores finance organization. The successful candidate builds and directs a multidisciplinary team of data scientists, applied scientists, economists, and product managers to deliver scalable solutions that fundamentally change how finance teams generate insights, automate workflows, and make decisions. As part of the WW Stores Finance leadership team, this leader partners with engineering, product, and finance stakeholders to translate emerging AI capabilities into production systems that deliver measurable improvements in speed, accuracy, and efficiency. The role's outputs directly inform VP/SVP/CFO/CEO leadership decisions and drive impact across the entire Stores P&L. Success requires translating complex technical concepts for finance domain experts and business leaders while maintaining deep technical credibility with science and engineering teams. The role demands both strategic vision—identifying high-impact opportunities where AI can transform finance operations—and execution excellence in coordinating project planning, resource allocation, and delivery across multiple concurrent initiatives. This leader establishes methodologies and models that enable Amazon finance to achieve step-change improvements in both the speed and quality of business insights, directly supporting critical processes including month-end reporting, quarterly guidance, annual planning cycles, and financial controllership. Key job responsibilities Transformation of Finance Workflows — Lead development of agentic AI solutions that automate routine finance tasks and transform how teams communicate business insights. Deploy these solutions across financial analysis, narrative generation, and dynamic table creation for month-end reporting and planning cycles. Partner with engineering and product teams to integrate these capabilities into production systems that directly support Stores Finance and FGBS automation goals, delivering measurable reductions in manual effort and cycle time. Science-Based Forecasting — Develop and deploy machine learning forecasts that integrate into existing planning processes including OP1, OP2, and quarterly guidance cycles. Partner with finance teams across WW Stores to iterate on forecast accuracy, applying these models either as alternative viewpoints to complement bottoms-up forecasts or as hands-off replacements for manual forecasting processes. Establish evaluation frameworks that demonstrate forecast performance against business benchmarks and drive adoption across critical planning workflows. Financial Controllership — Scale AI capabilities across controllership workstreams to improve reporting accuracy and automate manual processes. Leverage generative AI to identify financial risk through systematic pattern recognition in transaction data, account reconciliations, and variance analysis. Develop production systems that enhance decision-making speed and quality in financial close, audit preparation, and compliance reporting, delivering quantifiable improvements in error detection rates and process efficiency. About the team IPAT (Insights, Planning, Analytics, and Technology) is a team in the Worldwide Amazon Stores Finance organization composed of leaders across engineering, finance, product, and science. Our mission is to reimagine finance using technology and science to provide fast, efficient, and accurate insights that drive business decisions and strengthen governance. We are dedicated to improving financial operations through innovative applications of technology and science. Our work focuses on developing adaptive solutions for diverse financial use cases, applying AI to solve complex financial challenges, and conducting financial data analysis. Operating globally, we strive to develop adaptable solutions for diverse markets. We aim to advance financial science, continually improving accuracy, efficiency, and insight generation in support of Amazon's mission to be Earth's most customer-centric company.
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 an 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 cutting-edge 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 As an Applied Scientist, you will have access to large datasets with billions of images and video to build large-scale machine learning systems. Additionally, you will analyze and model terabytes of text, images, and other types of data to solve real-world problems and translate business and functional requirements into quick prototypes or proofs of concept. We are looking for smart scientists capable of using a variety of domain expertise combined with machine learning and statistical techniques to invent, design, evangelize, and implement state-of-the-art solutions for never-before-solved problems.
Sr. Economist, Advertising Incrementality Measurement
US, NY, New York
Do you want to lead the Ads industry and redefine how we measure the effectiveness of Amazon Ads business? Are you passionate about causal inference, Deep Learning/DNN, raising the science bar, and connecting leading-edge science research to Amazon-scale implementation? If so, come join Amazon Ads to be an Economist leader within our Advertising Incrementality Measurement science team! Our work builds the foundations for providing customer-facing experimentation tools, furthering internal research & development on Econometrics, and building out Amazon's advertising measurement offerings. Incrementality is a lynchpin for the next generation of Amazon Advertising measurement solutions and this role will play a key role in the release and expansion of these offerings. Key job responsibilities As an Economist leader within the Advertising Incrementality Measurement (AIM) science team, you are responsible for defining and executing on key workstreams within our overall causal measurement science vision. In particular, you can lead the development of experimental methodologies to measure ad effectiveness, and also build observational models that lay the foundations for understanding the impact of individual ad touchpoints for billions of daily ad interactions. You will work on a team of Applied Scientists, Economists, and Data Scientists, alongside a dedicated Engineering team, to work backwards from customer needs and translate product ideas into concrete science deliverables. You will be a thought leader for inventing scalable causal measurement solutions that support highly accurate and actionable insights--from defining and executing hundreds of thousands of RCTs, to developing an exciting science R&D agenda. You will be working with massive data and industry-leading partner scientists, while also interfacing with leadership to define our future vision. Your work will help shape the future of Amazon Advertising. About the team AIM is a cross disciplinary team of engineers, product managers, economists, data scientists, and applied scientists with a charter to build scientifically-rigorous causal inference methodologies at scale. Our job is to help customers cut through the noise of the modern advertising landscape and understand what actions, behaviors, and strategies actually have a real, measurable impact on key outcomes. The data we produce becomes the effective ground truth for advertisers and partners making decisions affecting millions in advertising spend.
Applied Scientist, Business Data Technologies
IN, KA, Bengaluru
RBS (Retail Business Services) Tech team works towards enhancing the customer experience (CX) and their trust in product data by providing technologies to find and fix Amazon CX defects at scale. Our platforms help in improving the CX in all phases of customer journey, including selection, discoverability & fulfilment, buying experience and post-buying experience (product quality and customer returns). The team also develops GenAI platforms for automation of Amazon Stores Operations. As a Sciences team in RBS Tech, we focus on foundational ML research and develop scalable state-of-the-art ML solutions to solve the problems covering customer experience (CX) and Selling partner experience (SPX). We work to solve problems related to multi-modal understanding (text and images), task automation through multi-modal LLM Agents, supervised and unsupervised techniques, multi-task learning, multi-label classification, aspect and topic extraction for Customer Anecdote Mining, image and text similarity and retrieval using NLP and Computer Vision for product groupings and identifying duplicate listings in product search results. Key job responsibilities As an Applied Scientist, you will be responsible to design and deploy scalable GenAI, NLP and Computer Vision solutions that will impact the content visible to millions of customer and solve key customer experience issues. You will develop novel LLM, deep learning and statistical techniques for task automation, text processing, image processing, pattern recognition, and anomaly detection problems. You will define the research and experiments strategy with an iterative execution approach to develop AI/ML models and progressively improve the results over time. You will partner with business and engineering teams to identify and solve large and significantly complex problems that require scientific innovation. You will independently file for patents and/or publish research work where opportunities arise. The RBS org deals with problems that are directly related to the selling partners and end customers and the ML team drives resolution to organization level problems. Therefore, the Applied Scientist role will impact the large product strategy, identifies new business opportunities and provides strategic direction which is very exciting.
Applied Scientist, Selection Monitoring
IN, KA, Bengaluru
Selection Monitoring team is responsible for making the biggest catalog on the planet even bigger. In order to drive expansion of the Amazon catalog, we develop advanced ML/AI technologies to process billions of products and algorithmically find products not already sold on Amazon. We work with structured, semi-structured and Visually Rich Documents using deep learning, NLP and image processing. The role demands a high-performing and flexible candidate who can take responsibility for success of the system and drive solutions from research, prototype, design, coding and deployment. We are looking for Applied Scientists to tackle challenging problems in the areas of Information Extraction, Efficient crawling at internet scale, developing ML models for website comprehension and agents to take multi-step decisions. You should have depth and breadth of knowledge in text mining, information extraction from Visually Rich Documents, semi structured data (HTML) and advanced machine learning. You should also have programming and design skills to manipulate Semi-Structured and unstructured data and systems that work at internet scale. You will encounter many challenges, including: - Scale (build models to handle billions of pages), - Accuracy (requirements for precision and recall) - Speed (generate predictions for millions of new or changed pages with low latency) - Diversity (models need to work across different languages, market places and data sources) You will help us to - Build a scalable system which can algorithmically extract information from world wide web. - Intelligently cluster web pages, segment and classify regions, extract relevant information and structure the data available on semi-structured web. - Build systems that will use existing Knowledge Base to perform open information extraction at scale from visually rich documents. Key job responsibilities - Use AI, NLP and advances in LLMs/SLMs and agentic systems to create scalable solutions for business problems. - Efficiently Crawl web, Automate extraction of relevant information from large amounts of Visually Rich Documents and optimize key processes. - Design, develop, evaluate and deploy, innovative and highly scalable ML models, esp. leveraging latest advances in RL-based fine tuning methods like DPO, GRPO etc. - Work closely with software engineering teams to drive real-time model implementations. - Establish scalable, efficient, automated processes for large scale model development, model validation and model maintenance. - Lead projects and mentor other scientists, engineers in the use of ML techniques. - Publish innovation in research forums.
2026 Applied Science Internships - ICLR
US, WA, Seattle
Unlock the Future with Amazon Science! Amazon is seeking boundary-pushing graduate student scientists who can turn revolutionary theory into awe-inspiring reality for internships in 2026. Join our team of visionary scientists and embark on a journey to harnessing the power of cutting-edge techniques in deep learning and revolutionize the fields of artificial intelligence, data science, speech recognition, text understanding, robotics and more. At Amazon, we don't just talk about innovation – we live and breathe it. You'll conducting research into the theory and application of deep learning. You will work on some of the most difficult problems in the industry with some of the best product managers, scientists, and software engineers in the industry. You will propose and deploy solutions that will likely draw from a range of scientific areas. Throughout your journey, you'll have access to unparalleled resources, including state-of-the-art computing infrastructure, cutting-edge research papers, and mentorship from industry luminaries. This immersive experience will not only sharpen your technical skills but also cultivate your ability to think critically, communicate effectively, and thrive in a fast-paced, innovative environment where bold ideas are celebrated. Join us at the forefront of applied science, where your contributions will shape the future of AI and propel humanity forward. Seize this extraordinary opportunity to learn, grow, and leave an indelible mark on the world of technology. Amazon has positions available for Applied Science Internships in, but not limited to Arlington, VA; Bellevue, WA; Boston, MA; New York, NY; Palo Alto, CA; San Diego, CA; Santa Clara, CA; Seattle, WA. Key job responsibilities We are particularly interested in candidates with expertise in: Machine Learning, Deep Learning, Robotics, LLMs, NLP/NLU, Gen AI, Transformers, Fine-Tuning, Recommendation Systems, Programming/Scripting Languages, Reinforcement Learning, Causal Inference and more. In this role, you will work alongside global experts to develop and implement novel, scalable algorithms and modeling techniques that advance the state-of-the-art in areas at the intersection of Reinforcement Learning and Optimization within Machine Learning. You will tackle challenging, groundbreaking research problems on production-scale data, with a focus on developing novel RL algorithms and applying them to complex, real-world challenges. The ideal candidate should possess the ability to work collaboratively with diverse groups and cross-functional teams to solve complex business problems. A successful candidate will be a self-starter, comfortable with ambiguity, with strong attention to detail and the ability to thrive in a fast-paced, ever-changing environment. A day in the life - Develop scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation. - Design, development and evaluation of highly innovative ML models for solving complex business problems. - Research and apply the latest ML techniques and best practices from both academia and industry. - Think about customers and how to improve the customer delivery experience. - Use and analytical techniques to create scalable solutions for business problems.
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