Social
Conversational AI

A quick guide to Amazon’s papers at ACL 2024

Work on large language models predominates, with a particular focus on model evaluation.

By Staff writer
August 12, 2024
5 min read
Share

Like the field of conversational AI in general, Amazon’s papers at this year’s meeting of the Association for Computational Linguistics (ACL) are dominated by work on large language models (LLMs). The properties that make LLMs’ outputs so extraordinary — such as their linguistic fluency and semantic coherence — are also notoriously difficult to quantify; as such, model evaluation has emerged as a particular area of focus. But Amazon’s papers explore a wide range of LLM-related topics, from applications such as code synthesis and automatic speech recognition to problems of LLM training and deployment, such as continual pretraining and hallucination mitigation. Papers accepted to the recently inaugurated Proceedings of the ACL are marked with asterisks.

Code synthesis

Fine-tuning language models for joint rewriting and completion of code with potential bugs
Dingmin Wang, Jinman Zhao, Hengzhi Pei, Samson Tan, Sheng Zha

Bug injection.png
Obtaining buggy partial code via bug injection. From “Fine-tuning language models for joint rewriting and completion of code with potential bugs”.

Continual pretraining

Efficient continual pre-training for building domain specific large language models*
Yong Xie, Karan Aggarwal, Aitzaz Ahmad

Data quality

A shocking amount of the web is machine translated: Insights from multi-way parallelism*
Brian Thompson, Mehak Dhaliwal, Peter Frisch, Tobias Domhan, Marcello Federico

Document summarization

The power of summary-source alignments
Ori Ernst, Ori Shapira, Aviv Slobodkin, Sharon Adar, Mohit Bansal, Jacob Goldberger, Ran Levy, Ido Dagan

Hallucination mitigation

Learning to generate answers with citations via factual consistency models
Rami Aly, Zhiqiang Tang, Samson Tan, George Karypis

Intent classification

Can your model tell a negation from an implicature? Unravelling challenges with intent encoders
Yuwei Zhang, Siffi Singh, Sailik Sengupta, Igor Shalyminov, Hwanjun Song, Hang Su, Saab Mansour

Irony recognition

MultiPICo: Multilingual perspectivist irony corpus
Silvia Casola, Simona Frenda, Soda Marem Lo, Erhan Sezerer, Antonio Uva, Valerio Basile, Cristina Bosco, Alessandro Pedrani, Chiara Rubagotti, Viviana Patti, Davide Bernardi

Knowledge grounding

Graph chain-of-thought: Augmenting large language models by reasoning on graphs
Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han

MATTER: Memory-augmented transformer using heterogeneous knowledge sources*
Dongkyu Lee, Chandana Satya Prakash, Jack G. M. FitzGerald, Jens Lehmann

Tree-of-traversals: A zero-shot reasoning algorithm for augmenting black-box language models with knowledge graphs
Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan

Tree of traversals.png
An example of how the tree-of-traversals method uses a knowledge graph interface for the query “What actor played in both Inception and Interstellar?” From "Tree-of-traversals: A zero-shot reasoning algorithm for augmenting black-box language models with knowledge graphs".

LLM decoding

BASS: Batched attention-optimized speculative sampling*
Haifeng Qian, Sujan Gonugondla, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Anoop Deoras

Machine translation

Impacts of misspelled queries on translation and product search
Greg Hanneman, Natawut Monaikul, Taichi Nakatani

The fine-tuning paradox: Boosting translation quality without sacrificing LLM abilities
David Stap, Eva Hasler, Bill Byrne, Christof Monz, Ke Tran

Model editing

Propagation and pitfalls: Reasoning-based assessment of knowledge editing through counterfactual tasks
Wenyue Hua, Jiang Guo, Marvin Dong, Henghui Zhu, Patrick Ng, Zhiguo Wang

ReCoE construction.png
Demonstration of the process used to construct data for the reasoning-based counterfactual-editing (ReCoE) dataset. Straight lines represent data sourced from existing datasets; dashed lines denote data derived from LLM generation; zigzag lines denote data obtained through the corruption of other data. From "Propagation and pitfalls: Reasoning-based assessment of knowledge editing through counterfactual tasks".

Model evaluation

Bayesian prompt ensembles: Model uncertainty estimation for black-box large language models
Francesco Tonolini, Jordan Massiah, Nikolaos Aletras, Gabriella Kazai

ConSiDERS—the-human evaluation framework: Rethinking human evaluation for generative large language models
Aparna Elangovan, Ling Liu, Lei Xu, Sravan Bodapati, Dan Roth

Factual confidence of LLMs: On reliability and robustness of current estimators
Matéo Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas Müller, Lluís Marquez

Fine-tuned machine translation metrics struggle in unseen domains
Vilém Zouhar, Shuoyang Ding, Anna Currey, Tatyana Badeka, Jenyuan Wang, Brian Thompson

Measuring question answering difficulty for retrieval-augmented generation
Matteo Gabburo, Nicolaas Jedema, Siddhant Garg, Leonardo Ribeiro, Alessandro Moschitti

Model robustness

Extreme miscalibration and the illusion of adversarial robustness
Vyas Raina, Samson Tan, Volkan Cevher, Aditya Rawal, Sheng Zha, George Karypis

Multimodal models

CaMML: Context-aware multimodal learner for large models
Yixin Chen, Shuai Zhang, Boran Han, Tong He, Bo Li

CAMML.png
The CaMML framework, which consists of a retriever, a perceiver and a generator. After receiving user query q, the CaMML retriever identifies relevant multimodal contexts C from the data store. Then the CaMML perceiver seamlessly integrates data of various modalities, effectively encoding long-context information and injecting it into the CaMML generator. This enables the prediction of responses that are conditioned on both the context and the query. From "CaMML: Context-aware multimodal learner for large models".

Multi-modal retrieval for large language model based speech recognition
Jari Kolehmainen, Aditya Gourav, Prashanth Gurunath Shivakumar, Yi Gu, Ankur Gandhe, Ariya Rastrow, Grant Strimel, Ivan Bulyko

REFINESUMM: Self-refining MLLM for generating a multimodal summarization dataset
Vaidehi Patil, Leonardo Ribeiro, Mengwen Liu, Mohit Bansal, Markus Dreyer

Ordinal classification

Exploring ordinality in text classification: A comparative study of explicit and implicit techniques
Siva Rajesh Kasa, Aniket Goel, Sumegh Roychowdhury, Karan Gupta, Anish Bhanushali, Nikhil Pattisapu, Prasanna Srinivasa Murthy

Question answering

Beyond boundaries: A human-like approach for question answering over structured and unstructured information sources*
Jens Lehmann, Dhananjay Bhandiwad, Preetam Gattogi, Sahar Vahdati

MinPrompt: Graph-based minimal prompt data augmentation for few-shot question answering
Xiusi Chen, Jyun-Yu Jiang, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Wei Wang

Synthesizing conversations from unlabeled documents using automatic response segmentation
Fanyou Wu, Weijie Xu, Chandan Reddy, Srinivasan Sengamedu, "SHS"

Reasoning

Eliciting better multilingual structured reasoning from LLMs through code
Bryan Li, Tamer Alkhouli, Daniele Bonadiman, Nikolaos Pappas, Saab Mansour

II-MMR: Identifying and improving multi-modal multi-hop reasoning in visual question answering*
Jihyung Kil, Farideh Tavazoee, Dongyeop Kang, Joo-Kyung Kim

Recommender systems

Generative explore-exploit: Training-free optimization of generative recommender systems using LLM optimizers
Besnik Fetahu, Zhiyu Chen, Davis Yoshida, Giuseppe Castellucci, Nikhita Vedula, Jason Choi, Shervin Malmasi

Towards translating objective product attributes into customer language
Ram Yazdi, Oren Kalinsky, Alexander Libov, Dafna Shahaf

Responsible AI

SpeechGuard: Exploring the adversarial robustness of multimodal large language models
Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki, Anshu Bhatia, Karel Mundnich, Saket Dingliwal, Nilaksh Das, Zejiang Hou, Goeric Huybrechts, Srikanth Vishnubhotla, Daniel Garcia-Romero, Sundararajan Srinivasan, Kyu Han, Katrin Kirchhoff

Text completion

Token alignment via character matching for subword completion*
Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen Tian, Zijian Wang, Sujan Gonugondla, Sanjay Krishna Gouda, Rob Kwiatkowski, Ramesh Nallapati, Bing Xiang

Token alignment.png
An illustration of token alignment process presented in "Token alignment via character matching for subword completion".

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Member of Technical Staff, Engineering Manager , Amazon AGI Lab
US, CA, San Francisco
Amazon launched the AGI Lab to develop foundational capabilities for useful AI agents. We built Nova Act - a new AI model trained to perform actions within a web browser. The team builds AI/ML infrastructure that powers our production systems to run performantly at high scale. We’re also enabling practical AI to make our customers more productive, empowered, and fulfilled. In particular, our work combines large language models (LLMs) with reinforcement learning (RL) to solve reasoning, planning, and world modeling in both virtual and physical environments. Our lab is a small, talent-dense team with the resources and scale of Amazon. Each team in the lab has the autonomy to move fast and the long-term commitment to pursue high-risk, high-payoff research. We’re entering an exciting new era where agents can redefine what AI makes possible. We’d love for you to join our lab and build it from the ground up! Key job responsibilities This role will lead a team of SDEs building AI agents infrastructure from launch to scale. The role requires the ability to span across ML/AI system architecture and infrastructure. You will work closely with application developers and scientists to have a impact on the Agentic AI industry. We're looking for a Software Development Manager who is energized by building high performance systems, making an impact and thrives in fast-paced, collaborative environments. About the team Check out the Nova Act tools our team built on on nova.amazon.com/act
Data Scientist, AWS Quick Data
US, CA, Santa Clara
Amazon Quick Suite is an enterprise AI platform that transforms how organizations work with their data and knowledge. Combining generative AI-powered search, deep research capabilities, intelligent agents and automations, and comprehensive business intelligence, Quick Suite serves tens of thousands of users. Our platform processes thousands of queries monthly, helping teams make faster, data-driven decisions while maintaining enterprise-grade security and governance. From natural language interactions with complex datasets to automated workflows and custom AI agents, Quick Suite is redefining workplace productivity at unprecedented scale. We are seeking a Data Scientist II to join our Quick Data team, focusing on evaluation and benchmarking data development for Quick Suite features, with particular emphasis on Research and other generative AI capabilities. Our mission is to engineer high-quality datasets that are essential to the success of Amazon Quick Suite. From human evaluations and Responsible AI safeguards to Retrieval-Augmented Generation and beyond, our work ensures that Generative AI is enterprise-ready, safe, and effective for users at scale. As part of our diverse team—including data scientists, engineers, language engineers, linguists, and program managers—you will collaborate closely with science, engineering, and product teams. We are driven by customer obsession and a commitment to excellence. Key job responsibilities In this role, you will leverage data-centric AI principles to assess the impact of data on model performance and the broader machine learning pipeline. You will apply Generative AI techniques to evaluate how well our data represents human language and conduct experiments to measure downstream interactions. Specific responsibilities include: * Design and develop comprehensive evaluation and benchmarking datasets for Quick Suite AI-powered features * Leverage LLMs for synthetic data corpora generation; data evaluation and quality assessment using LLM-as-a-judge settings * Create ground truth datasets with high-quality question-answer pairs across diverse domains and use cases * Lead human annotation initiatives and model evaluation audits to ensure data quality and relevance * Develop and refine annotation guidelines and quality frameworks for evaluation tasks * Conduct statistical analysis to measure model performance, identify failure patterns, and guide improvement strategies * Collaborate with ML scientists and engineers to translate evaluation insights into actionable product improvements * Build scalable data pipelines and tools to support continuous evaluation and benchmarking efforts * Contribute to Responsible AI initiatives by developing safety and fairness evaluation datasets About the team Why AWS? Amazon Web Services (AWS) is the world’s most comprehensive and broadly adopted cloud platform. We pioneered cloud computing and never stopped innovating — that’s why customers from the most successful startups to Global 500 companies trust our robust suite of products and services to power their businesses. Inclusive Team Culture Here at AWS, it’s in our nature to learn and be curious. Our employee-led affinity groups foster a culture of inclusion that empower us to be proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon conferences, inspire us to never stop embracing our uniqueness. Mentorship & Career Growth We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional. Work/Life Balance We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why we strive for flexibility as part of our working culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve in the cloud. Hybrid Work We value innovation and recognize this sometimes requires uninterrupted time to focus on a build. We also value in-person collaboration and time spent face-to-face. Our team affords employees options to work in the office every day or in a flexible, hybrid work model near one of our U.S. Amazon offices.
Data Scientist II, FinAuto
IN, KA, Bengaluru
Interested to build the next generation Financial systems that can handle billions of dollars in transactions? Interested to build highly scalable next generation systems that could utilize Amazon Cloud? Massive data volume + complex business rules in a highly distributed and service oriented architecture, a world class information collection and delivery challenge. Our challenge is to deliver the software systems which accurately capture, process, and report on the huge volume of financial transactions that are generated each day as millions of customers make purchases, as thousands of Vendors and Partners are paid, as inventory moves in and out of warehouses, as commissions are calculated, and as taxes are collected in hundreds of jurisdictions worldwide. Key job responsibilities • Understand the business and discover actionable insights from large volumes of data through application of machine learning, statistics or causal inference. • Analyse and extract relevant information from large amounts of Amazon’s historical transactions data to help automate and optimize key processes • Research, develop and implement novel machine learning and statistical approaches for anomaly, theft, fraud, abusive and wasteful transactions detection. • Use machine learning and analytical techniques to create scalable solutions for business problems. • Identify new areas where machine learning can be applied for solving business problems. • Partner with developers and business teams to put your models in production. • Mentor other scientists and engineers in the use of ML techniques. A day in the life • Understand the business and discover actionable insights from large volumes of data through application of machine learning, statistics or causal inference. • Analyse and extract relevant information from large amounts of Amazon’s historical transactions data to help automate and optimize key processes • Research, develop and implement novel machine learning and statistical approaches for anomaly, theft, fraud, abusive and wasteful transactions detection. • Use machine learning and analytical techniques to create scalable solutions for business problems. • Identify new areas where machine learning can be applied for solving business problems. • Partner with developers and business teams to put your models in production. • Mentor other scientists and engineers in the use of ML techniques. About the team The FinAuto TFAW(theft, fraud, abuse, waste) team is part of FGBS Org and focuses on building applications utilizing machine learning models to identify and prevent theft, fraud, abusive and wasteful(TFAW) financial transactions across Amazon. Our mission is to prevent every single TFAW transaction. As a Machine Learning Scientist in the team, you will be driving the TFAW Sciences roadmap, conduct research to develop state-of-the-art solutions through a combination of data mining, statistical and machine learning techniques, and coordinate with Engineering team to put these models into production. You will need to collaborate effectively with internal stakeholders, cross-functional teams to solve problems, create operational efficiencies, and deliver successfully against high organizational standards.
Applied Scientist, FinAuto
IN, KA, Bengaluru
Interested to build the next generation Financial systems that can handle billions of dollars in transactions? Interested to build highly scalable next generation systems that could utilize Amazon Cloud? Massive data volume + complex business rules in a highly distributed and service oriented architecture, a world class information collection and delivery challenge. Our challenge is to deliver the software systems which accurately capture, process, and report on the huge volume of financial transactions that are generated each day as millions of customers make purchases, as thousands of Vendors and Partners are paid, as inventory moves in and out of warehouses, as commissions are calculated, and as taxes are collected in hundreds of jurisdictions worldwide. Key job responsibilities • Understand the business and discover actionable insights from large volumes of data through application of machine learning, statistics or causal inference. • Analyse and extract relevant information from large amounts of Amazon’s historical transactions data to help automate and optimize key processes • Research, develop and implement novel machine learning and statistical approaches for anomaly, theft, fraud, abusive and wasteful transactions detection. • Use machine learning and analytical techniques to create scalable solutions for business problems. • Identify new areas where machine learning can be applied for solving business problems. • Partner with developers and business teams to put your models in production. • Mentor other scientists and engineers in the use of ML techniques. A day in the life • Understand the business and discover actionable insights from large volumes of data through application of machine learning, statistics or causal inference. • Analyse and extract relevant information from large amounts of Amazon’s historical transactions data to help automate and optimize key processes • Research, develop and implement novel machine learning and statistical approaches for anomaly, theft, fraud, abusive and wasteful transactions detection. • Use machine learning and analytical techniques to create scalable solutions for business problems. • Identify new areas where machine learning can be applied for solving business problems. • Partner with developers and business teams to put your models in production. • Mentor other scientists and engineers in the use of ML techniques. About the team The FinAuto TFAW(theft, fraud, abuse, waste) team is part of FGBS Org and focuses on building applications utilizing machine learning models to identify and prevent theft, fraud, abusive and wasteful(TFAW) financial transactions across Amazon. Our mission is to prevent every single TFAW transaction. As a Machine Learning Scientist in the team, you will be driving the TFAW Sciences roadmap, conduct research to develop state-of-the-art solutions through a combination of data mining, statistical and machine learning techniques, and coordinate with Engineering team to put these models into production. You will need to collaborate effectively with internal stakeholders, cross-functional teams to solve problems, create operational efficiencies, and deliver successfully against high organizational standards.
Applied Scientist II, HST Health Evaluation
IN, KA, Bengaluru
Amazon Health Services (One Medical) About Us: At Health AI, we're revolutionizing healthcare delivery through innovative AI-enabled solutions. As part of Amazon Health Services and One Medical, we're on a mission to make quality healthcare more accessible while improving patient outcomes. Our work directly impacts millions of lives by empowering patients and enabling healthcare providers to deliver more meaningful care. Role Overview: We're seeking an Applied Scientist to join our dynamic team in building state of the art AI/ML solutions for healthcare. This role offers a unique opportunity to work at the intersection of artificial intelligence and healthcare, developing solutions that will shape the future of medical services delivery. Key job responsibilities • Lead end-to-end development of AI/ML solutions for Amazon Health organization, including Amazon Pharmacy and One Medical • Research, design, and implement state-of-the-art machine learning models, with a focus on Large Language Models (LLMs) and Visual Language Models (VLMs) • Optimize and fine-tune models for production deployment, including model distillation for improved latency • Drive scientific innovation while maintaining a strong focus on practical business outcomes • Collaborate with cross-functional teams to translate complex technical solutions into tangible customer benefits • Contribute to the broader Amazon Health scientific community and help shape our technical roadmap
Mixed Signal Design Engineer, Amazon Center for Quantum Computing
US, CA, Pasadena
The Amazon Center for Quantum Computing in Pasadena, CA, is looking to hire an Applied Scientist specializing in Mixed-Signal Design. Working alongside other scientists and engineers, you will design and validate hardware performing the control and readout functions for AWS quantum processors. Candidates must have a solid background in mixed-signal design at the printed circuit board (PCB) level. Working effectively within a cross-functional team environment is critical. The ideal candidate will have demonstrated the capability to contribute to all phases of product life cycle development, from requirements gathering to verification. Diverse Experiences Amazon values diverse experiences. Even if you do not meet all of the preferred qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn’t followed a traditional path, or includes alternative experiences, don’t let it stop you from applying. Work/Life Balance We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why we strive for flexibility as part of our working culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve in the cloud. Inclusive Team Culture Here at Amazon, it’s in our nature to learn and be curious. Our employee-led affinity groups foster a culture of inclusion that empower us to be proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences, inspire us to never stop embracing our uniqueness. Mentorship and Career Growth We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional. Key job responsibilities Our scientists and engineers collaborate across diverse teams and projects to offer state of the art, cost effective solutions for the control of Amazon quantum processor systems. You’ll bring a passion for innovation, collaboration, and mentoring to: Solve layered technical problems, often ones not encountered before, across our hardware stack. Develop requirements with key system stakeholders, including quantum device, test and measurement, and cryogenic hardware teams. Design, implement, test, deploy, and maintain innovative solutions that meet both strict performance and cost metrics. Research enabling control system technologies necessary for Amazon to produce commercially viable quantum computers.
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, 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