Social
Conversational AI

A quick guide to Amazon's 40+ papers at EMNLP 2023

Research on natural-language understanding seeks to harness the power of large language models, while query reformulation and text summarization emerge as topics of particular interest.

By Staff writer
December 6, 2023
6 min read
Share

Natural-language understanding (NLU) has long been a central focus of the papers that Amazon researchers publish at the Conference on Empirical Methods in Natural-Language Processing (EMNLP), but at this year's conference, which starts today, Amazon's NLU research shows a particular interest in harnessing the power of large language models (LLMs). Question answering also remains an active research topic, while query reformulation and text summarization emerge as new areas of concentration.

Automatic speech recognition

AdaBERT-CTC: Leveraging BERT-CTC for text-only domain adaptation in ASR
Tyler Vuong, Karel Mundnich, Dhanush Bekal, Veera Raghavendra Elluru, Srikanth Ronanki, Sravan Bodapati

Continual learning

Coordinated replay sample selection for continual federated learning
Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta 

Data extraction

InsightNet: Structured insight mining from customer feedback
Sandeep Mukku, Manan Soni, Chetan Aggarwal, Jitenkumar Rana, Promod Yenigalla, Rashmi Patange, Shyam Mohan

Knowledge-selective pretraining for attribute value extraction
Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chenwei Zhang, Bing Yin, William Wang, Xiaodan Zhu

Data selection

Influence scores at scale for efficient language data sampling
Nikhil Anand, Joshua Tan, Maria Minakova

Document understanding

A multi-modal multilingual benchmark for document image classification
Yoshinari Fujinuma, Siddharth Varia, Nishant Sankaran, Bonan Min, Srikar Appalaraju, Yogarshi Vyas

Semantic matching for text classification with complex class descriptions
Brian de Silva, Kuan-Wen Huang, Gwang Lee, Karen Hovsepian, Yan Xu, Mingwei Shen

Embodied task completion

Multimodal embodied plan prediction augmented with synthetic embodied dialogue
Aishwarya Padmakumar, Mert Inan, Spandana Gella, Patrick Lange, Dilek Hakkani-Tür

Entity linking

MReFinED: An efficient end-to-end multilingual entity linking system
Peerat Limkonchotiwat, Weiwei Cheng, Christos Christodoulopoulos, Amir Saffari, Jens Lehmann

Few-shot learning

Automated few-shot classification with instruction-finetuned language models
Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Wilson

AuT-Few.png
A schematic view of the Aut-Few prompt automation method. From "Automated few-shot classification with instruction-finetuned language models".

Information retrieval

Deep metric learning to hierarchically rank—An application in product retrieval
Kee Kiat Koo, Ashutosh Joshi, Nishaanth Reddy, Ismail Tutar, Vaclav Petricek, Changhe Yuan, Karim Bouyarmane

KD-Boost: Boosting real-time semantic matching in e-commerce with knowledge distillation
Sanjay Agrawal, Vivek Sembium, Ankith M S

CESAR.png
The CESAR framework automatically merges compound tasks — such as, in this example, keyword-controlled generation and act-grounded generation. From "CESAR: Automatic induction of compositional instructions for multi-turn dialogs".

Multi-teacher distillation for multilingual spelling correction
Jingfen Zhang, Xuan Guo, Sravan Bodapati, Christopher Potts

Instruction tuning

CESAR: Automatic induction of compositional instructions for multi-turn dialogs
Taha Aksu, Devamanyu Hazarika, Shikib Mehri, Seokhwan Kim, Dilek Hakkani-Tür, Yang Liu, Mahdi Namazifar

LLM hallucination

INVITE: A testbed of automatically generated invalid questions to evaluate large language models for hallucinations
Anil Ramakrishna, Rahul Gupta, Jens Lehmann, Morteza Ziyadi

Machine learning

Efficient long-range transformers: You need to attend more, but not necessarily at every layer
Qingru Zhang, Dhananjay Ram, Cole Hawkins, Sheng Zha, Tuo Zhao

Natural-language processing

NameGuess: Column name expansion for tabular data
Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Shen Wang, Huzefa Rangwala, George Karypis

Natural-language understanding

Adversarial robustness for large-language NER models using disentanglement and word attributions
Xiaomeng Jin, Bhanu Vinzamuri, Sriram Venkatapathy, Heng Ji, Pradeep Natarajan

Measuring and mitigating dialog-to-API constraint violations of in-context learning
Shufan Wang, Sebastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang

Intent classification.png
Overview of the pretraining of an intent-aware encoder. Given an utterance, x1, from the pretraining corpus, Amazon researchers generate a pseudo intent name, y1pseudo, using labels from the intent-role-labeling (IRL) tagger. The model is then optimized by pulling the gold utterance x1gold, the gold intent y1, and the pseudo intent, y1pseudo, close to the input utterance, x1, in the embedding space. From "Pre-training intent-aware encoders for zero- and few-shot intent classification".

MultiCoNER v2: A large multilingual dataset for fine-grained and noisy named entity recognition
Besnik Fetahu, Zhiyu Chen, Sudipta Kar, Oleg Rokhlenko, Shervin Malmasi

Pre-training intent-aware encoders for zero- and few-shot intent classification
Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli

Personalization

Personalized dense retrieval on global index for voice-enabled conversational systems
Masha Belyi, Charlotte Dzialo, Chaitanya Dwivedi, Prajit Reddy Muppidi, Kanna Shimizu

Retrieve and copy: Scaling ASR personalization to large catalogs
Sai Muralidhar Jayanthi, Devang Kulshreshtha, Saket Dingliwal, Srikanth Ronanki, Sravan Bodapati

Query reformulation

CL-QR: Cross-lingual enhanced query reformulation for multi-lingual conversational AI agents
Zhongkai Sun, Zhengyang Zhao, Sixing Lu, Chengyuan Ma, Xiaohu Liu, Xing Fan, Wei (Sawyer) Shen, Chenlei (Edward) Guo

Graph meets LLM: A novel approach to collaborative filtering for robust conversational understanding
Zheng Chen, Ziyan Jiang, Fan Yang, Eunah Cho, Xing Fan, Xiaojiang Huang, Yanbin Lu, Aram Galstyan

Improving contextual query rewrite for conversational AI agents through user-preference feedback learning
Zhongkai Sun, Yingxue Zhou, Jie Hao, Xing Fan, Yanbin Lu, Chengyuan Ma, Wei (Sawyer) Shen, Chenlei (Edward) Guo

Question-answer databases

Protege: Prompt-based diverse question generation from web articles
Vinayak Puranik, Anirban Majumder, Vineet Chaoji

QUADRo: Dataset and models for question-answer database retrieval
Stefano Campese, Ivano Lauriola, Alessandro Moschitti

Question answering

Strong and efficient baselines for open domain conversational question answering
Andrei C. Coman, Gianni Barlacchi, Adrià de Gispert

Tokenization consistency matters for generative models on extractive NLP tasks
Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Yang Wang, Zhiheng Huang

Too much of product information: Don’t worry, let’s look for evidence!
Aryan Jain, Jitenkumar Rana, Chetan Aggarwal

Reasoning

Plan, verify and switch: Integrated reasoning with diverse x-of-thoughts
Tengxiao Liu, Qipeng Guo, Yuqing Yang, Xiangkun Hu, Yue Zhang, Xipeng Qiu, Zheng Zhang 

XOT.png
An overview of the x-of-thought (XoT) problem-solving framework, which integrates chain-of-thought (CoT) and program-of-thought (PoT) methods with the researchers' novel equation-of-thought (EoT) approach. From "Plan, verify and switch: Integrated reasoning with diverse x-of-thoughts".

Responsible AI

Geographical erasure in language generation
Pola Schwöbel, Jacek Golebiowski, Michele Donini, Cédric Archambeau, Danish Pruthi

Speech translation

End-to-end single-channel speaker-turn aware conversational speech translation
Juan Pablo Zuluaga Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico

Text summarization

Enhancing abstractiveness of summarization models through calibrated distillation
Hwanjun Song, Igor Shalyminov, Hang Su, Siffi Singh, Kaisheng Yao, Saab Mansour

Generating summaries with controllable readability levels
Leonardo Ribeiro, Mohit Bansal, Markus Dreyer

Improving consistency for text summarization with energy functions
Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang

InstructPTS: Instruction-tuning LLMs for product title summarization
Besnik Fetahu, Zhiyu Chen, Oleg Rokhlenko, Shervin Malmasi

Multi document summarization evaluation in the presence of damaging content
Avshalom Manevich, David Carmel, Nachshon Cohen, Elad Kravi, Ori Shapira

Re-examining summarization evaluation across multiple quality criteria
Ori Ernst, Ori Shapira, Ido Dagan, Ran Levy

Topic modeling

DeTiME: Diffusion-enhanced topic modeling using encoder-decoder based LLM
Weijie Xu, Wenxiang Hu, Fanyou Wu, Srinivasan Sengamedu, "SHS"

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, WA, Bellevue
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Economics - Intern - EU Stores, Economic Decision Science
GB, London
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
Applied Scientist
US, WA, Seattle
At Amazon Selection and Catalog Systems (ASCS), our mission is to power the online buying experience for customers worldwide so they can find, discover, and buy any product they want. We innovate on behalf of our customers to ensure uniqueness and consistency of product identity and to infer relationships between products in Amazon Catalog to drive the selection gateway for the search and browse experiences on the website. We're solving a fundamental AI challenge: establishing product identity and relationships at unprecedented scale. Using Generative AI, Visual Language Models (VLMs), and multimodal reasoning, we determine what makes each product unique and how products relate to one another across Amazon's catalog. The scale is staggering: billions of products, petabytes of multimodal data, millions of sellers, dozens of languages, and infinite product diversity—from electronics to groceries to digital content. The research challenges are immense. GenAI and VLMs hold transformative promise for catalog understanding, but we operate where traditional methods fail: ambiguous problem spaces, incomplete and noisy data, inherent uncertainty, reasoning across both images and textual data, and explaining decisions at scale. Establishing product identities and groupings requires sophisticated models that reason across text, images, and structured data—while maintaining accuracy and trust for high-stakes business decisions affecting millions of customers daily. Amazon's Item and Relationship Platform group is looking for an innovative and customer-focused applied scientist to help us make the world's best product catalog even better. In this role, you will partner with technology and business leaders to build new state-of-the-art algorithms, models, and services to infer product-to-product relationships that matter to our customers. You will pioneer advanced GenAI solutions that power next-generation agentic shopping experiences, working in a collaborative environment where you can experiment with massive data from the world's largest product catalog, tackle problems at the frontier of AI research, rapidly implement and deploy your algorithmic ideas at scale, across millions of customers. Key job responsibilities Key job responsibilities include: * Formulate open research problems at the intersection of GenAI, multimodal reasoning, and large-scale information retrieval—defining the scientific questions that transform ambiguous, real-world catalog challenges into publishable, high-impact research * Push the boundaries of VLMs, foundation models, and agentic architectures by designing novel approaches to product identity, relationship inference, and catalog understanding—where the problem complexity (billions of products, multimodal signals, inherent ambiguity) demands methods that don't yet exist * Advance the science of efficient model deployment—developing distillation, compression, and LLM/VLM serving optimization strategies that preserve frontier-level multimodal reasoning in compact, production-grade architectures while dramatically reducing latency, cost, and infrastructure footprint at billion-product scale * Make frontier models reliable—advancing uncertainty calibration, confidence estimation, and interpretability methods so that frontier-scale GenAI systems can be trusted for autonomous catalog decisions impacting millions of customers daily * Own the full research lifecycle from problem formulation through production deployment—designing rigorous experiments over petabytes of multimodal data, iterating on ideas rapidly, and seeing your research directly improve the shopping experience for hundreds of millions of customers * Shape the team's research vision by defining technical roadmaps that balance foundational scientific inquiry with measurable product impact * Mentor scientists and engineers on advanced ML techniques, experimental design, and scientific rigor—building deep organizational capability in GenAI and multimodal AI * Represent the team in the broader science community—publishing findings, delivering tech talks, and staying at the forefront of GenAI, VLM, and agentic system research
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 monthly newsletter

Amazon.com | Conditions of Use | Privacy | © 1996-2026 Amazon.com, Inc. or its affiliates

Social