Social
Conversational AI

A quick guide to Amazon’s 45-plus NAACL papers

The breadth and originality of Amazon’s natural-language-processing research are on display at the annual meeting of the North American chapter of the Association for Computational Linguistics.

By Staff writer
July 7, 2022
6 min read
Share

Amazon’s 45-plus papers at the annual meeting of the North American chapter of the Association for Computational Linguistics, which begins next week, sorted by research area.

Continual learning

Lifelong pretraining: Continually adapting language models to emerging corpora
Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew O. Arnold, Xiang Ren

Local-to-global learning for iterative training of production SLU models on new features
Yulia Grishina, Daniil Sorokin

Overcoming catastrophic forgetting during domain adaptation of seq2seq language generation
Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao, Xiaohu Liu, Xing Fan, Chenlei (Edward) Guo, Yang Liu

Overcoming catastrophic forgetting.png
In "Overcoming catastrophic forgetting during domain adaptation of seq2seq language generation", Amazon researchers propose a method for estimating how much data representations shift when an existing model is trained on a new task (right).

Temporal generalization for spoken language understanding
Judith Gaspers, Anoop Kumar, Greg Ver Steeg, Aram Galstyan

Data augmentation

Constraining word alignments with posterior regularization for label transfer
Kevin Martin Jose, Thomas Gueudré

Word alignments.png
An example of the difficulty in using word alignment to transfer textual labels from one language to another. In English, the article "the" is assigned the label "o", for "other"; in French, the abbreviated article is combined with its noun, and both receive the same label ("type"). From "Constraining word alignments with posterior regularization for label transfer".

Controlled data generation via insertion operations for NLU
Manoj Kumar, Haidar Khan, Yuval Merhav, Wael Hamza, Anna Rumshisky, Rahul Gupta

Efficient semi supervised consistency training for natural language understanding
George Leung, Joshua Tan

Learning to generate examples for semantic processing tasks
Danilo Croce, Simone Filice, Giuseppe Castellucci, Roberto Basili

Dialogue

Learning dialogue representations from consecutive utterances
Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang

Massive-scale decoding for text generation using lattices
Jiacheng Xu, Siddhartha Reddy Jonnalagadda, Greg Durrett

Entity linking, resolution, and typing

Contrastive representation learning for cross-document coreference resolution of events and entities
Benjamin Hsu, Graham Horwood

Improving entity disambiguation by reasoning over a knowledge base
Tom Ayoola, Joseph Fisher, Andrea Pierleoni

ReFinED: An efficient zero-shot-capable approach to end-to-end entity linking
Tom Ayoola, Shubhi Tyagi, Joseph Fisher, Christos Christodoulopoulos, Andrea Pierleoni

Instilling type knowledge in language models via multi-task QA
Shuyang Li, Mukund Sridhar, Chandana Satya Prakash, Jin Cao, Wael Hamza, Julian McAuley

Explainable AI

Entailment trees.png
In "Entailment tree explanations via iterative retrieval-generation reasoner", Amazon researchers propose a method for explaining the outputs of large language models by logically recombining premises extracted from supporting textual evidence.

Entailment tree explanations via iterative retrieval-generation reasoner
Danilo Neves Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henry Zhu, Xinchi Chen, Zhiheng Huang, Peng Xu, Andrew O. Arnold, Dan Roth

Locally aggregated feature attribution on natural language model understanding
Sheng Zhang, Jin Wang, Haitao Jiang, Rui Song

Extreme multilabel classification

Augmenting training data for massive semantic matching models in low-traffic e-commerce stores
Ashutosh Joshi, Shankar Vishwanath, Choon Hui Teo, Vaclav Petricek, Vishy Vishwanathan, Rahul Bhagat, Jonathan May

Extreme zero shot learning for extreme text classification
Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit S. Dhillon

Federated learning

Federated learning with noisy user feedback
Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta

Keyword spotting

AB/BA analysis: A framework for estimating keyword spotting recall improvement while maintaining audio privacy
Raphael Petegrosso, Vasistakrishna Baderdinni, Thibaud Senechal, Benjamin L. Bullough

Machine translation

CoCoA-MT: A dataset and benchmark for contrastive controlled MT with application to formality
Maria Nadejde, Anna Currey, Benjamin Hsu, Xing Niu, Marcello Federico, Georgiana Dinu

Dynamic pulling.png
In federated learning, distributed copies of a neural network are trained locally, and only their updates (red) are sent to a central model. "Training mixed-domain translation models via federated learning" introduces a technique called dynamic pulling, in which distributed models with large shifts in parameter values between training rounds (lower left) see their parameters pulled into the central model separately from those of models with smaller shifts.

The devil is in the details: On the pitfalls of vocabulary selection in neural machine translation
Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, Felix Hieber

Training mixed-domain translation models via federated learning
Peyman Passban, Tanya G. Roosta, Rahul Gupta, Ankit Chadha, Clement Chung

Multitask learning

Asynchronous convergence in multi-task learning via knowledge distillation from converged tasks
Weiyi Lu, Sunny Rajagopalan, Priyanka Nigam, Jaspreet Singh, Xiaodi Sun, Yi Xu, Belinda Zeng, Trishul Chilimbi

Exploring the role of task transferability in large-scale multi-task learning
Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, George Karypis

Named-entity recognition

Dynamic gazetteer integration in multilingual models for cross-lingual and cross-domain named entity recognition
Besnik Fetahu, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi

NER-MQMRC: Formulating named entity recognition as multi question machine reading comprehension
Anubhav Shrimal, Avi Jain, Kartik Mehta, Promod Yenigalla

Question answering

Answer consolidation: Formulation and benchmarking
Wenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, Muhao Chen

Paragraph-based transformer pre-training for multi-sentence inference
Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti

PerKGQA: Question answering over personalized knowledge graphs
Ritam Dutt, Kasturi Bhattacharjee, Rashmi Gangadharaiah, Dan Roth, Carolyn Penstein Rosé

Product answer generation from heterogeneous sources: A new benchmark and best practices
Xiaoyu Shen, Gianni Barlacchi, Marco Del Tredici, Weiwei Cheng, Adria de Gispert, Bill Byrne

Recommender systems

CERES: Pretraining of graph-conditioned transformer for semi-structured session data
Rui Feng, Chen Luo, Qingyu Yin, Bing Yin, Tuo Zhao, Chao Zhang

Self-learning

Failure point isolation.png
In "FPI: Failure point isolation in large-scale conversational assistants", Amazon researchers propose a method for deducing where in a conversational agent's processing pipeline an error has occurred.

FPI: Failure point isolation in large-scale conversational assistants
Rinat Khaziev, Usman Shahid, Tobias Röding, Rakesh Chada, Emir Kapanci, Pradeep Natarajan

Scalable and robust self-learning for skill routing in large-scale conversational AI systems
Mohammad Kachuee, Jinseok Nam, Sarthak Ahuja, Jin-Myung Won, Sungjin Lee

Self-aware feedback-based self-learning in large-scale conversational AI
Pragaash Ponnusamy, Clint Solomon Mathialagan, Gustavo Aguilar, Chengyuan Ma, Chenlei (Edward) Guo

Task-oriented parsing.png
An example of task-oriented semantic parsing, which converts natural language into a formal representation that an AI agent can act on. From "Compositional task-oriented parsing as abstractive question answering".

Semantic parsing

Compositional task oriented parsing as abstractive question answering
Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie

SeqZero: Few-shot compositional semantic parsing with sequential prompts and zero-shot models
Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin, Diyi Yang

Task adaptation

Attention fusion: A light yet efficient late fusion mechanism for task adaptation in NLU
Jin Cao, Chandana Satya Prakash, Wael Hamza

Empowering parameter-efficient transfer learning by recognizing the kernel structure in attention
Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tür

Text mining

Distantly supervised aspect clustering and naming for e-commerce reviews
Prateek Sircar, Aniket Chakrabarti, Deepak Gupta, Anirban Majumdar

Efficient few-shot fine-tuning for opinion summarization
Arthur Bražinskas, Ramesh Nallapati, Mohit Bansal, Markus Dreyer

FactGraph: Evaluating factuality in summarization with semantic graph representations
Leonardo F. R. Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal

Knowledge selection.png
An example of how a conversational agent might incorporate facts gleaned form online sources (white boxes) into its conversational replies (blue boxes). From "Enhanced knowledge selection for grounded dialogues via document semantic graphs".

Enhanced knowledge selection for grounded dialogues via document semantic graphs
Sha Li, Madhi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tür

Retrieval-augmented multilingual keyphrase generation with retriever-generator iterative training
Yifan Gao, Qingyu Yin, Zheng Li, Rui Meng, Tong Zhao, Bing Yin, Irwin King, Michael R. Lyu

What do users care about? Detecting actionable insights from user feedback
Kasturi Bhattacharjee, Rashmi Gangadharaiah, Kathleen McKeown, Dan Roth

Text-to-speech

Empathic machines: using intermediate features as levers to emulate emotions in text-to-speech systems
Saiteja Kosgi, Sarath Sivaprasad, Niranjan Pedanekar, Anil Nelakanti, Vineet Gandhi

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Applied Scientist / ML scientist, EU Prime and Marketing Analytics & Science (PRIMAS)
ES, B, Barcelona
Are you interested in defining the science strategy that enables Amazon to market to millions of customers based on their lifecycle needs rather than one-size-fits-all campaigns? We are seeking a Applied Scientist to lead the science strategy for our Lifecycle Marketing Experimentation roadmap within the PRIMAS (Prime & Marketing analytics and science) team. The position is open to candidates in Amsterdam and Barcelona. In this role, you will own the end-to-end science approach that enables EU marketing to shift from broad, generic campaigns to targeted, cohort-based marketing that changes customer behavior. This is a high-ambiguity, high-impact role where you will define what problems are worth solving, build the science foundation from scratch, and influence senior business leaders on marketing strategy. You will work directly with Business Directors and channel leaders to solve critical business problems: how do we win back customers lost to competitors, convert Young Adults to Prime, and optimize marketing spend by de-averaging across customer cohorts. Key job responsibilities Science Strategy & Leadership: 1. Own the end-to-end science strategy for lifecycle marketing, defining the roadmap across audience targeting, behavioral modeling, and measurement 2. Navigate high ambiguity in defining customer journey frameworks and behavioral models – our most challenging science problem with no established playbook 3. Lead strategic discussions with business leaders translating business needs into science solutions and building trust across business and tech partners 4. Mentor and guide a team of 2-3 scientists and BIEs on technical execution while contributing hands-on to the hardest problems Advanced Customer Behavior Modeling: 1. Build sophisticated propensity models identifying customer cohorts based on lifecycle stage and complex behavioral patterns (e.g., Bargain hunters, Young adults Prime prospects) 2. Define customer journey frameworks using advanced techniques (Hidden Markov Models, sequential decision-making) to model how customers transition across lifecycle stages 3. Identify which customer behaviors and triggers drive lifecycle progression and what messaging/levers are most effective for each cohort 4. Integrate 1P behavioral data with 2P survey insights to create rich, actionable audience definitions Measurement & Cross-Workstream Integration: 1. Partner with measurement scientist to design experiments (RCTs) that isolate audience targeting effects from creative effects 2. Ensure audience definitions, journey models, and measurement frameworks work coherently across Meta, LiveRamp, and owned channels 3. Establish feedback loops connecting measurement insights back to model improvements About the team The PRIMAS (Prime & Marketing Analytics and Science) is the team that support the science & analytics needs of the EU Prime and Marketing organization, an org that supports the Prime and Marketing programs in European marketplaces and comprises 250-300 employees. The PRIMAS team, is part of a larger tech tech team of 100+ people called WIMSI (WW Integrated Marketing Systems and Intelligence). WIMSI core mission is to accelerate marketing technology capabilities that enable de-averaged customer experiences across the marketing funnel: awareness, consideration, and conversion.
Applied Scientist II, Central Machine Learning
IN, KA, Bengaluru
Do you want to join an innovative team of scientists who use machine learning and statistical techniques to create state-of-the-art solutions for providing better value to Amazon’s customers? Do you want to build and deploy advanced algorithmic systems that help optimize millions of transactions every day? Are you excited by the prospect of analyzing and modeling terabytes of data to solve real world problems? Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company? Do you like to innovate and simplify? If yes, then you may be a great fit to join the Machine Learning and Data Sciences team for India Consumer Businesses. If you have an entrepreneurial spirit, know how to deliver, love to work with data, are deeply technical, highly innovative and long for the opportunity to build solutions to challenging problems that directly impact the company's bottom-line, we want to talk to you. Major 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 models for predictive learning - 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
Applied Scientist, EU INTech Consumer Selection, Tamale
ES, M, Madrid
At Amazon, we are committed to being the Earth's most customer-centric company. The European International Technology group (EU INTech) owns the enhancement and delivery of Amazon's engineering to all the varied customers and cultures of the world. We do this through a combination of partnerships with other Amazon technical teams and our own innovative new projects. You will be joining the Tamale team to work on Haul. As part of EU INTech and Haul, Tamale strives to create a discovery-driven shopping experience using challenging machine learning and ranking solutions. You will be exposed to large-scale recommendation systems, multi-objective optimization, and state-of-the-art deep learning architectures, and you'll be part of a key effort to improve our customers' browsing experience by building next-generation ranking models for Amazon Haul's endless scroll experience. We are looking for a passionate, talented, and inventive Scientist with a strong machine learning background to help build industry-leading ranking solutions. We strongly value your hard work and obsession to solve complex problems on behalf of Amazon customers. Key job responsibilities We look for applied scientists who possess a wide variety of skills. As the successful applicant for this role, you will work closely with your business partners to identify opportunities for innovation. You will apply machine learning solutions to optimize multi-objective ranking, improve discovery engagement through contextual signals, and scale ranking systems across multiple marketplaces. You will work with business leaders, scientists, and product managers to translate business and functional requirements into concrete deliverables, including the design, development, testing, and deployment of highly scalable distributed ranking services. You will be part of a team of scientists and engineers working on solving ranking and personalization challenges at scale. You will be able to influence the scientific roadmap of the team, setting the standards for scientific excellence. You will be working with state-of-the-art architectures and real-time feature serving systems. Your work will improve the experience of millions of daily customers using Amazon Haul worldwide. You will have the chance to have great customer impact and continue growing in one of the most innovative companies in the world. You will learn a huge amount - and have a lot of fun - in the process!
Applied Scientist, International Machine Learning
IN, HR, Gurugram
Do you want to join an innovative team of scientists who use machine learning and statistical techniques to create state-of-the-art solutions for providing better value to Amazon’s customers? Do you want to build and deploy advanced ML systems that help optimize millions of transactions every day? Are you excited by the prospect of analyzing and modeling terabytes of data to solve real-world problems? Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company? Do you like to innovate and simplify? If yes, then you may be a great fit to join the Machine Learning team for International Emerging Stores (IES). Machine Learning, Big Data and related quantitative sciences have been strategic to Amazon from the early years. Amazon has been a pioneer in areas such as recommendation engines, ecommerce fraud detection and large-scale optimization of fulfillment center operations. As Amazon has rapidly grown and diversified, the opportunity for applying machine learning has exploded. We have a very broad collection of practical problems where machine learning systems can dramatically improve the customer experience, reduce cost, and drive speed and automation. These include product bundle recommendations for millions of products, safeguarding financial transactions across by building the risk models, improving catalog quality via extracting product attribute values from structured/unstructured data for millions of products, enhancing address quality by powering customer suggestions We are developing state-of-the-art machine learning solutions to accelerate the Amazon India growth story. Amazon is an exciting place to be at for a machine learning practitioner. We have the eagerness of a fresh startup to absorb machine learning solutions, and the scale of a mature firm to help support their development at the same time. As part of the International Machine Learning team, you will get to work alongside brilliant minds motivated to solve real-world machine learning problems that make a difference to millions of our customers. We encourage thought leadership and blue ocean thinking in ML. 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, develop, evaluate and deploy, innovative and highly scalable ML models Work closely with software engineering teams to drive real-time model implementations Work closely with business partners to identify problems and propose machine learning solutions Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model maintenance Work proactively with engineering teams and product managers to evangelize new algorithms and drive the implementation of large-scale complex ML models in production Leading projects and mentoring other scientists, engineers in the use of ML techniques About the team International Machine Learning Team is responsible for building novel ML solutions across International Emerging Store (India, MENA, Far-East, LatAm) problems and impact the bottom-line and top-line of India business. Learn more about our team from https://www.amazon.science/working-at-amazon/how-rajeev-rastogis-machine-learning-team-in-india-develops-innovations-for-customers-worldwide
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, 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.
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