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
Data Scientist II, PXT Central Science
US, VA, Arlington
We are seeking an exceptional Data Scientist to join our team in PXT Central Science. The ideal candidate will thrive in a dynamic, multifaceted role where you'll translate complex business challenges into rigorous quantitative frameworks, extract actionable insights from structured and unstructured datasets, and architect science-backed, scalable solutions that elevate the experience of our 1 million+ employees worldwide. If you're energized by the opportunity to apply data science to our mission of making Amazon Earth's Best Employer, we want to hear from you. Key job responsibilities • Own the design, development, and maintenance of scalable models and prototypes leveraging statistical, machine learning, or GenAI methodologies to enhance employee experience. • Partner with scientists, engineers, and product leaders to solve for employee experience defects using scientific approaches, building new services and tools that deliverable measurable impact. • Author and maintain detailed technical documentation related to the projects you drive. • Communicate results to diverse audiences of varying technical background with effective writing, visualizations, and presentations • Stay current with emerging methods and technologies, and implement them strategically to amplify the team’s impact. About the team The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, machine learning, and Generative AI to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science, engineering, and UX to develop and deliver solutions that measurably achieve this goal.
Applied Scientist I, Amazon Fulfillment Technology , Amazon Fulfillment Technologies (AFT)
US, WA, Bellevue
The Amazon Fulfillment Technologies (AFT) Science team is looking for an exceptional Applied Scientist, with strong optimization and analytical skills, to develop production solutions for one of the most complex systems in the world: Amazon’s Fulfillment Network. At AFT Science, we design, build and deploy optimization, simulation, and machine learning solutions to power the production systems running at world wide Amazon Fulfillment Centers. We solve a wide range of problems that are encountered in the network, including labor planning and staffing, demand prioritization, pick assignment and scheduling, and flow process optimization. We are tasked to develop innovative, scalable, and reliable science-driven solutions that are beyond the published state of art in order to run frequently (ranging from every few minutes to every few hours per use case) and continuously in our large scale network. Key job responsibilities As an Applied Scientist, you will work with other scientists, software engineers, product managers, and operations leaders to develop scientific solutions and analytics using a variety of tools and observe direct impact to process efficiency and associate experience in the fulfillment network. Key responsibilities include: * Develop an understanding and domain knowledge of operational processes, system architecture and functions, and business requirements * Deep dive into data and code to identify opportunities for continuous improvement and/or disruptive new approach * Develop scalable mathematical models for production systems to derive optimal or near-optimal solutions for existing and new challenges * Create prototypes and simulations for agile experimentation of devised solutions * Advocate technical solutions to business stakeholders, engineering teams, and senior leadership * Partner with engineers to integrate prototypes into production systems * Design experiment to test new or incremental solutions launched in production and build metrics to track performance About the team Amazon Fulfillment Technology (AFT) designs, develops and operates the end-to-end fulfillment technology solutions for all Amazon Fulfillment Centers (FC). We harmonize the physical and virtual world so Amazon customers can get what they want, when they want it. The AFT Science team has expertise in operations research, optimization, scheduling, planning, simulation, and machine learning. We also have domain expertise in the operational processes within the FCs and their defects. We prioritize advancements that support AFT tech teams and focus areas rather than specific fields of research or individual business partners. We influence each stage of innovation from inception to deployment which includes both developing novel solutions or improving existing approaches. Resulting production systems rely on a diverse set of technologies, our teams therefore invest in multiple specialties as the needs of each focus area evolves.
Data Scientist II, PXT Central Science
US, WA, Seattle
We are seeking an exceptional Data Scientist to join our team in PXT Central Science. The ideal candidate will thrive in a dynamic, multifaceted role where you'll translate complex business challenges into rigorous quantitative frameworks, extract actionable insights from structured and unstructured datasets, and architect science-backed, scalable solutions that elevate the experience of our 1 million+ employees worldwide. If you're energized by the opportunity to apply data science to our mission of making Amazon Earth's Best Employer, we want to hear from you. Key job responsibilities • Own the design, development, and maintenance of scalable models and prototypes leveraging statistical, machine learning, or GenAI methodologies to enhance employee experience. • Partner with scientists, engineers, and product leaders to solve for employee experience defects using scientific approaches, building new services and tools that deliverable measurable impact. • Author and maintain detailed technical documentation related to the projects you drive. • Communicate results to diverse audiences of varying technical background with effective writing, visualizations, and presentations • Stay current with emerging methods and technologies, and implement them strategically to amplify the team’s impact. About the team The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, machine learning, and Generative AI to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science, engineering, and UX to develop and deliver solutions that measurably achieve this goal.
Applied Scientist II, Alexa International Team
US, WA, Bellevue
Alexa International is looking for a passionate, talented, and inventive Applied Scientist to help build industry-leading technology with Large Language Models (LLMs) and multimodal systems, requiring strong deep learning and generative models knowledge. You will contribute to developing novel solutions and deliver high-quality results that impact Alexa's international products and services. Key job responsibilities As an Applied Scientist with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with LLMs. Your work will directly impact our international customers in the form of products and services that make use of digital assistant technology. You will leverage Amazon's heterogeneous data sources, unique and diverse international customer nuances and large-scale computing resources to accelerate advances in text, voice, and vision domains in a multimodal setup. The ideal candidate possesses a solid understanding of machine learning, natural language understanding, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environments to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and collaborate effectively with cross-functional teams. A day in the life * Analyze, understand, and model customer behavior and the customer experience based on large-scale data. * Build novel online & offline evaluation metrics and methodologies for multimodal personal digital assistants. * Fine-tune/post-train LLMs using techniques like SFT, DPO, RLHF, and RLAIF. * Set up experimentation frameworks for agile model analysis and A/B testing. * Collaborate with partner teams on LLM evaluation frameworks and post-training methodologies. * Contribute to end-to-end delivery of solutions from research to production, including reusable science components. * Communicate solutions clearly to partners and stakeholders. * Contribute to the scientific community through publications and community engagement.
Applied Scientist, Last Mile
US, WA, Bellevue
Amazon’s Last Mile Team is looking for a passionate individual with strong optimization and analytical skills to join its Last Mile Science team in the endeavor of designing and improving the most complex planning of delivery network in the world. Last Mile builds global solutions that enable Amazon to attract an elastic supply of drivers, companies, and assets needed to deliver Amazon's and other shippers' volumes at the lowest cost and with the best customer delivery experience. Last Mile Science team owns the core decision models in the space of jurisdiction planning, delivery channel and modes network design, capacity planning for on the road and at delivery stations, routing inputs estimation and optimization. Our research has direct impact on customer experience, driver and station associate experience, Delivery Service Partner (DSP)’s success and the sustainable growth of Amazon. Optimizing the last mile delivery requires deep understanding of transportation, supply chain management, pricing strategies and forecasting. Only through innovative and strategic thinking, we will make the right capital investments in technology, assets and infrastructures that allows for long-term success. Our team members have an opportunity to be on the forefront of supply chain thought leadership by working on some of the most difficult problems in the industry with some of the best product managers, scientists, and software engineers in the industry. Key job responsibilities Candidates will be responsible for developing solutions to better manage and optimize delivery capacity in the last mile network. The successful candidate should have solid research experience in one or more technical areas of Operations Research or Machine Learning. These positions will focus on identifying and analyzing opportunities to improve existing algorithms and also on optimizing the system policies across the management of external delivery service providers and internal planning strategies. They require superior logical thinkers who are able to quickly approach large ambiguous problems, turn high-level business requirements into mathematical models, identify the right solution approach, and contribute to the software development for production systems. To support their proposals, candidates should be able to independently mine and analyze data, and be able to use any necessary programming and statistical analysis software to do so. Successful candidates must thrive in fast-paced environments, which encourage collaborative and creative problem solving, be able to measure and estimate risks, constructively critique peer research, and align research focuses with the Amazon's strategic needs.
Applied Scientist II, Alexa International Team
US, WA, Bellevue
Alexa International is looking for a passionate, talented, and inventive Applied Scientist to help build industry-leading technology with Large Language Models (LLMs) and multimodal systems, requiring strong deep learning and generative models knowledge. You will contribute to developing novel solutions and deliver high-quality results that impact Alexa's international products and services. Key job responsibilities As an Applied Scientist with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with LLMs. Your work will directly impact our international customers in the form of products and services that make use of digital assistant technology. You will leverage Amazon's heterogeneous data sources, unique and diverse international customer nuances and large-scale computing resources to accelerate advances in text, voice, and vision domains in a multimodal setup. The ideal candidate possesses a solid understanding of machine learning, natural language understanding, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environments to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and collaborate effectively with cross-functional teams. A day in the life * Analyze, understand, and model customer behavior and the customer experience based on large-scale data. * Build novel online & offline evaluation metrics and methodologies for multimodal personal digital assistants. * Fine-tune/post-train LLMs using techniques like SFT, DPO, RLHF, and RLAIF. * Set up experimentation frameworks for agile model analysis and A/B testing. * Collaborate with partner teams on LLM evaluation frameworks and post-training methodologies. * Contribute to end-to-end delivery of solutions from research to production, including reusable science components. * Communicate solutions clearly to partners and stakeholders. * Contribute to the scientific community through publications and community engagement.
2026 Fall Quantum Applied Science Internship, Center for Quantum Computing
US, CA, Pasadena
The Amazon Web Services (AWS) Center for Quantum Computing (CQC) is a multi-disciplinary team of theoretical and experimental physicists, materials scientists, and hardware and software engineers on a mission to develop a fault-tolerant quantum computer. Throughout your internship journey, you'll have access to unparalleled resources, including state-of-the-art computing infrastructure, cutting-edge research papers, and mentorship from industry luminaries. This immersive experience will not only sharpen your technical skills but also cultivate your ability to think critically, communicate effectively, and thrive in a fast-paced, innovative environment where bold ideas are celebrated. Join us at the forefront of applied science, where your contributions will shape the future of Quantum Computing and propel humanity forward. Seize this extraordinary opportunity to learn, grow, and leave an indelible mark on the world of technology. Amazon has positions available for Quantum Research Science and Applied Science Internships in Santa Clara, CA and Pasadena, CA. We are particularly interested in candidates with expertise in any of the following areas: superconducting qubits, cavity/circuit QED, quantum optics, open quantum systems, superconductivity, electromagnetic simulations of superconducting circuits, microwave engineering, benchmarking, quantum error correction, fabrication, etc. Key job responsibilities In this role, you will work alongside global experts to develop and implement novel, scalable solutions that advance the state-of-the-art in the areas of quantum computing. You will tackle challenging, groundbreaking research problems, work with leading edge technology, focus on highly targeted customer use-cases, and launch products that solve problems for Amazon customers. The ideal candidate should possess the ability to work collaboratively with diverse groups and cross-functional teams to solve complex business problems. A successful candidate will be a self-starter, comfortable with ambiguity, with strong attention to detail and the ability to thrive in a fast-paced, ever-changing environment. About the team Diverse Experiences AWS values diverse experiences. Even if you do not meet all of the qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn’t followed a traditional path, or includes alternative experiences, don’t let it stop you from applying. Why 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 (gender diversity) 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.
Senior Applied Scientist, Alexa International
US, WA, Bellevue
Alexa International Science team is looking for a passionate, talented, and inventive Senior Applied Scientist to help build industry-leading technology with Large Language Models (LLMs) and multimodal systems, requiring strong deep learning and generative models knowledge. At this level, you will drive cross-team scientific strategy, influence partner teams, and deliver solutions that have broad impact across Alexa's international products and services. Key job responsibilities As a Senior Applied Scientist with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with LLMs, particularly delivering industry-leading scientific research and applied AI for multi-lingual applications — a challenging area for the industry globally. Your work will directly impact our global customers in the form of products and services that support Alexa+. You will leverage Amazon's heterogeneous data sources and large-scale computing resources to accelerate advances in text, speech, and vision domains. The ideal candidate possesses a solid understanding of machine learning, speech and/or natural language processing, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environment, like to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and are able to influence and align multiple teams around a shared scientific vision.
Language Data Scientist, Alexa International
US, WA, Bellevue
Amazon is seeking a Language Data Scientist to join the Alexa International science team as domain expert. This role focuses on expanding analysis and evaluation of conversational interaction data deliverables. The Language Data Scientist is an expert in conversation assessment processes, working closely with a team of skilled machine learning scientists and engineers, and is a key member in developing new conventions for relevant annotation workflows. The Language Data Scientist will be own unique data analysis and research requests that support the training and evaluation of LLMs and machine learning models, and the overall processing of a data collection. Key job responsibilities To be successful in this role, you must have a passion for data, efficiency, and accuracy. Specifically, you will: - Own data analyses for customer-facing features, including launch go/no-go metrics for new features and accuracy metrics for existing features - Handle unique data analysis requests from a range of stakeholders, including quantitative and qualitative analyses to elevate customer experience with speech interfaces - Lead and evaluate changing dialog evaluation conventions, test tooling developments, and pilot processes to support expansion to new data areas - Continuously evaluate workflow tools and processes and offer solutions to ensure they are efficient, high quality, and scalable - Provide expert support for a large and growing team of data analysts - Provide support for ongoing and new data collection efforts as a subject matter expert on conventions and use of the data - Conduct research studies to understand speech and customer-Alexa interactions - Collaborate with scientists and product managers, and other stakeholders in defining and validating customer experience metrics
Applied Scientist II, Alexa International Team
US, WA, Bellevue
Alexa International is looking for a passionate, talented, and inventive Applied Scientist to help build industry-leading technology with Large Language Models (LLMs) and multimodal systems, requiring strong deep learning and generative models knowledge. You will contribute to developing novel solutions and deliver high-quality results that impact Alexa's international products and services. Key job responsibilities As an Applied Scientist with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with LLMs. Your work will directly impact our international customers in the form of products and services that make use of digital assistant technology. You will leverage Amazon's heterogeneous data sources, unique and diverse international customer nuances and large-scale computing resources to accelerate advances in text, voice, and vision domains in a multimodal setup. The ideal candidate possesses a solid understanding of machine learning, natural language understanding, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environments to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and collaborate effectively with cross-functional teams. A day in the life * Analyze, understand, and model customer behavior and the customer experience based on large-scale data. * Build novel online & offline evaluation metrics and methodologies for multimodal personal digital assistants. * Fine-tune/post-train LLMs using techniques like SFT, DPO, RLHF, and RLAIF. * Set up experimentation frameworks for agile model analysis and A/B testing. * Collaborate with partner teams on LLM evaluation frameworks and post-training methodologies. * Contribute to end-to-end delivery of solutions from research to production, including reusable science components. * Communicate solutions clearly to partners and stakeholders. * Contribute to the scientific community through publications and community engagement.
See more jobs
View from space of a connected network around planet Earth representing the Internet of Things.
Get more from Amazon Science
Subscribe to our newsletter

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

Social