Social
Conversational AI

A quick guide to Amazon’s 50-plus papers at EMNLP 2024

Large language models predominate, both as a research subject themselves and as tools for researching topics of particular interest to Amazon, such as speech, recommendations, and information retrieval.

By Staff writer
November 14, 2024
7 min read
Share

Large language models (LLMs) have come to dominate the field of natural-language processing, so it’s no surprise that they also dominate the research that Amazon scientists are presenting at this year’s Conference on Empirical Methods in Natural-Language Processing (EMNLP). LLM training is the topic with the greatest number of Amazon papers, followed closely by strategies for mitigating misinformation in LLMs’ outputs — including but not limited to hallucinations. At the same time, a number of papers apply LLMs to topics of traditional interest at Amazon, such as speech, recommender systems, and information retrieval. (Papers marked with asterisks were accepted to Findings of EMNLP.)

AI agents

MARCO: Multi-agent real-time chat orchestration
Anubhav Shrimal, Shervin Malmasi, Kriti Biswas, Swarnalatha Raghuraman, Anish Nediyanchath, Yi Zhang, Promod Yenigalla

Code generation

CodeFort: Robust training for code generation models
Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

Socratic human feedback (SoHF): Expert steering strategies for LLM code generation
Subramanian Chidambaram, Erran Li, Min Bai, Xiaopeng LI, Kaixiang Lin, Xiong Zhou, Alex C. Williams

Structured object language modeling (SoLM): Native structured objects generation conforming to complex schemas with self-supervised denoising
Amir Tavanaei, Kee Kiat Koo, Hayreddin Ceker, Shaobai Jiang, Qi Li, Julien Han, Karim Bouyarmane

Contrastive decoding

Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung

Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM.png
Given a simple question with clues, contrastive decoding could have an “obvious blindness” (e.g., assigning higher probability to an uncommon answer, such as "invertebrate", than to the most obvious answer, "bees"). In contrast, the asymptotic probability decoding proposed in "Explaining and improving contrastive decoding by extrapolating the probabilities of a huge and hypothetical LM" correctly assigns the highest probability to "bees" by leveraging the probabilities from multiple LMs of different sizes.

Data integration

ASTRA: Automatic schema matching using machine translation
Tarang Chugh, Deepak Zambre

Learning from natural language explanations for generalizable entity matching
Somin Wadhwa, Adit Krishnan, Runhui Wang, Byron C. Wallace, Chris (Luyang) Kong

Pretraining and finetuning language models on geospatial networks for accurate address matching
Saket Maheshwary, Arpan Paul, Saurabh Sohoney

Retrieval augmented spelling correction for e-commerce applications
Xuan Guo, Rohit Patki, Dante Everaert, Christopher Potts

Dataset distillation

Textual dataset distillation via language model embedding
Yefan Tao, Chris (Luyang) Kong, Andrey Kan, Laurent Callot

Textual dataset distillation via language model embedding: DaLLME.png
The DaLLME framework proposed in "Textual dataset distillation via language model embedding" begins by using a language model to transform raw textual data into embedding vectors. A set of distilled vectors is then derived in the embedding space, through a process designed to encapsulate maximum informational content. Finally, the vec2text model translates these distilled vectors back into textual form.

Document understanding

DocKD: Knowledge distillation from LLMs for open-world document understanding models
Sungnyun Kim, Haofu Liao, Srikar Appalaraju, Peng Tang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Stefano Soatto

Information retrieval

Evaluating D-MERIT of partial-annotation on information retrieval
Royi Rassin, Yaron Fairstein, Oren Kalinsky, Guy Kushilevitz, Nachshon Cohen, Alexander Libov, Yoav Goldberg

Identifying high consideration e-commerce search queries
Zhiyu Chen, Jason Choi, Besnik Fetahu, Shervin Malmasi

Learning when to retrieve, what to rewrite, and how to respond in conversational QA*
Nirmal Roy, Leonardo Ribeiro, Rexhina Blloshmi, Kevin Small

Natural-language understanding

Intent detection in the age of LLMs
Gaurav Arora, Shreya Jain, Srujana Merugu

Intent detection in the age of LLMs.png
"Intent detection in the age of LLMs" proposes a methodology for adaptive in-context learning and chain-of-thought-based intent detection using LLMs.

Predicting entity salience in extremely short documents
Ben Bullough, Harrison Lundberg, Chen Hu, Weihang Xiao

LLM evaluation

AXCEL: Automated eXplainable consistency evaluation using LLMs*
P Aditya Sreekar, Sahil Verma, Suransh Chopra, Sarik Ghazarian, Abhishek Persad, Narayanan Sadagopan

Precise model benchmarking with only a few observations
Riccardo Fogliato, Pratik Patil, Nil-Jana Akpinar, Mathew Monfort

LLM fine tuning

AdaZeta: Adaptive zeroth-order tensor-train adaption for memory-efficient large language models fine-tuning
Yifan Yang, Kai Zhen, Ershad Banijamali, Thanasis Mouchtaris, Zheng Zhang

RoseLoRA: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning
Haoyu Wang, Tianci Liu, Ruirui Li, Monica Cheng, Tuo Zhao, Jing Gao

RoseLoRA.png
The row- and column-wise sparse low-rank adaptation (RoseLoRA) framework proposed in "RoseLoRA: Row and column-wise sparse low-rank adaptation of pre-trained language model for knowledge editing and fine-tuning".

LLMs for speech

Speechworthy instruction-tuned language models
Hyundong Cho, Nicolaas Jedema, Leonardo Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, Jonathan May

LLM misinformation mitigation

ECON: On the detection and resolution of evidence conflicts
Cheng Jiayang, Chunkit Chan, Qianqian Zhuang, Lin Qiu, Tianhang Zhang, Tengxiao Liu, Yangqiu Song, Yue Zhang, Pengfei Liu, Zheng Zhang

Generative subgraph retrieval for knowledge graph–grounded dialog generation
Jinyoung Park, Minseok Joo, Joo-Kyung Kim, Hyunwoo J. Kim

HalluMeasure: Fine-grained hallucination measurement using chain-of-thought reasoning
Shayan Ali Akbar, Md Mosharaf Hossain, Tess Wood, Si-Chi Chin, Erica Salinas, Victor Alvarez, Erwin Cornejo

Knowledge-centric hallucination detection
Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Zheng Zhang, Yue Zhang

LLM reasoning

Auto-evolve: Enhancing large language model’s performance via self-reasoning framework*
Krishna Aswani, Alex Lu, Pranav Patankar, Priya Dhalwani, Iris Tan, Jayant Ganeshmohan, Simon Lacasse

LLM self-correction

LLM self-correction with DeCRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints
Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

DeCRIM.png
In the DeCRIM pipeline proposed in "LLM self-correction with DeCRIM: Decompose, critique, and refine for enhanced following of instructions with multiple constraints", an LLM first generates a response to a user request. The Decomposer then breaks down the request into granular constraints, and the Critic model gives feedback on whether the response meets those constraints. If it does, the response is output; if not, the LLM uses the feedback to refine the response.

LLM training

Dancing in chains: Reconciling instruction following and faithfulness in language models
Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

DEM: Distribution edited model for training with mixed data distributions
Dhananjay Ram, Aditya Rawal, Momchil Hardalov, Nikolaos Pappas, Sheng Zha

DEM: Distribution Edited Model for Training with Mixed Data Distributions
The distribution-edited model (ΘD) described in "DEM: Distribution edited model for training with mixed data distributions" results from fine-tuning a pretrained model (Θ) on n individual data distributions (Di) and combining the resulting models with basic element-wise vector operations. Here, the extracted distribution vectors (∆ΘDi ) are multiplied by weight coefficients, and the weighted sum is added to the base model.

Evolutionary contrastive distillation for language model alignment
Julian Katz-Samuels, Zheng Li, Hyokun Yun, Priyanka Nigam, Yi Xu, Vaclav Petricek, Bing Yin, Trishul Chilimbi

Hop, skip, jump to convergence: Dynamics of learning rate transitions for improved training of large language models
Shreyas Subramanian, Vignesh Ganapathiraman, Corey Barrett

Learning from relevant subgoals in successful dialogs using iterative training for task-oriented dialog systems
Magdalena Kaiser, Patrick Ernst, Gyuri Szarvas

Quality matters: Evaluating synthetic data for tool-using LLMs
Shadi Iskander, Nachshon Cohen, Zohar Karnin, Ori Shapira, Sofia Tolmach

Query autocompletion

AmazonQAC: A large-scale, naturalistic query autocomplete dataset
Dante Everaert, Rohit Patki, Tianqi Zheng, Christopher Potts

DiAL: Diversity aware listwise ranking for query auto-complete
Sonali Singh, Sachin Farfade, Prakash Mandayam Comar

Question answering

RAG-QA arena: Evaluating domain robustness for long-form retrieval-augmented question answering
Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

Retrieving contextual information for long-form question answering using weak supervision
Philipp Christmann, Svitlana Vakulenko, Ionut Teodor Sorodoc, Bill Byrne, Adrià de Gispert

Recommender systems

Efficient pointwise-pairwise learning-to-rank for news recommendation
Nithish Kannen Senthilkumar, Yao Ma, Gerrit van den Burg, Jean Baptiste Faddoul

Efficient pointwise-pairwise learning-to-rank for news recommendation.png
An illustration of the GLIMPSE framework proposed in "Efficient pointwise-pairwise learning-to-rank for news recommendation". GLIMPSE adopts a multitask approach in which a pretrained language model is fine-tuned on both the relevance prediction task and the pairwise-preference task. During inference, the relevance predictions are used to produce an initial pointwise ranking, which is subsequently improved by one or more right-to-left (RTL) passes using pairwise comparisons.

PEARL: Preference extraction with exemplar augmentation and retrieval with LLM agents
Vijit Malik, Akshay Jagatap, Vinayak Puranik, Anirban Majumder

Sequential LLM framework for fashion recommendation
Han Liu, Xianfeng Tang, Tianlang Chen, Jiapeng Liu, Indu Indu, Henry Peng Zou, Peng Dai, Roberto Fernandez Galan, Mike Porter, Dongmei Jia, Ning Zhang, Lian Xiong

Responsible AI

Attribute controlled fine-tuning for large language models: A case study on detoxification
Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris

FLIRT: Feedback loop in-context red teaming
Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta

Order of magnitude speedups for LLM membership inference
Rongting Zhang, Martin Bertran Lopez, Aaron Roth

Synthetic data generation

CorrSynth: A correlated sampling method for diverse dataset generation from LLMs
Suhas Kowshik, Abhishek Divekar, Vijit Malik

A Correlated Sampling Method for Diverse Dataset Generation from LLMs
"CorrSynth: A correlated sampling method for diverse dataset generation from LLMs" introduces a sampling method that uses anti-correlation between examples rather than few-shot generation.

DATA ADVISOR: Dynamic data curation for safety alignment of large language models
Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan

Evaluating differentially private synthetic data generation in high-stakes domains
Krithika Ramesh, Nupoor Gandhi, Pulkit Madaan, Lisa Bauer, Charith Peris, Anjalie Field

SYNTHESIZRR: Generating diverse datasets with retrieval augmentation
Abhishek Divekar, Greg Durrett

Abstract depiction of the SYNTHESIZRR procedure
Abstract depiction of the procedure proposed in "SYNTHESIZRR: Generating diverse datasets with retrieval augmentation". The content sourcing stage retrieves K unique documents {r1,...,rK} from a large corpus for each in-context covariate xICL. The task-inversion stage uses a parameterized context refinement prompt, Pτ, which takes parameters Rinv (inversion instruction), rk (a retrieved document), and V(yICL) (the verbalized target label). A generalist teacher LLM autoregressively generates a synthetic covariate. Each in-context example thus produces K unique synthetic examples {x̃1,..., x̃K}, which we include in the dataset with target yICL.

Text classification

Distance-aware calibration for pre-trained language models*
Alberto Gasparin, Gianluca Detommaso

Performance-guided LLM knowledge distillation for efficient text classification at scale

Flavio Di Palo, Prateek Singhi, Bilal Fadlallah

Prompt-tuned muti-task taxonomic transformer (PTMTTaxoFormer)
Rajashekar Vasantha, Nhan Nguyen, Yue Zhang

Text summarization

Salient information prompting to steer content in prompt-based abstractive summarization
Lei Xu, Asad Karim, Saket Dingliwal, Aparna Elangovan

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Applied Scientist I, Sponsored Products and Brands Agent
US, NY, New York
The Sponsored Products and Brands team at Amazon Ads is re-imagining the advertising landscape through generative AI technologies, revolutionizing how millions of customers discover products and engage with brands across Amazon.com and beyond. We are at the forefront of re-inventing advertising experiences, bridging human creativity with artificial intelligence to transform every aspect of the advertising lifecycle from ad creation and optimization to performance analysis and customer insights. We are a passionate group of innovators dedicated to developing responsible and intelligent AI technologies that balance the needs of advertisers, enhance the shopping experience, and strengthen the marketplace. If you're energized by solving complex challenges and pushing the boundaries of what's possible with AI, join us in shaping the future of advertising. About the team SPB Agent team's vision is to build a highly personalized and context-aware agentic advertiser guidance system that seamlessly integrates Large Language Models (LLMs) with sophisticated tooling, operating across all experiences. The SPB-Agent is the central agent that interfaces with advertisers across Ads Console, Selling Partner portals (Seller Central, KDP, Vendor Central), and internal Sales systems. We identify high-impact opportunities spanning from strategic product guidance to granular optimization and deliver them through personalized, scalable experiences grounded in state-of-the-art agent architectures, reasoning frameworks, sophisticated tool integration, and model customization approaches including fine-tuning, MCP, and preference optimization. This presents an exceptional opportunity to shape the future of e-commerce advertising through advanced AI technology at unprecedented scale, creating solutions that directly impact millions of advertisers.
Applied Scientist
DE, BE, Berlin
At Audible, we believe stories have the power to transform lives. It’s why we work with some of the world’s leading creators to produce and share audio storytelling with our millions of global listeners. We are dreamers and inventors who come from a wide range of backgrounds and experiences to empower and inspire each other. Imagine your future with us. ABOUT THIS ROLE As an Applied Scientist, you will solve large complex real-world problems at scale, draw inspiration from the latest science and technology to empower undefined/untapped business use cases, delve into customer requirements, collaborate with tech and product teams on design, and create production-ready models that span various domains, including Machine Learning (ML), Artificial Intelligence (AI) and Generative AI, Natural Language Processing (NLP), Reinforcement Learning (RL), real-time and distributed systems. ABOUT YOU Your work will focus on inventing or adapting scientific approaches, models, and algorithms driven by customer needs at the project level. You will develop components and/or end-to-end solutions that are deployed into production or directly support production systems, delivering consistently high-quality work that meets both scientific and engineering best practices. You will develop reusable science components and services that resolve architecture deficiencies and customers’ pain points, while making technical trade-offs for long-term/short- term. You will work semi-autonomously to deliver solutions, contribute to research papers at peer-reviewed venues when appropriate, and document your work thoroughly to enable others to understand and reproduce it. Your decision-making will consistently incorporate robust, data-driven business and technical judgment. You will collaborate with other scientists to raise the bar of both scientific and engineering complexity for the team and to foster valuable scientific partnership opportunities to help/guide science decisions. We work in a highly collaborative, fast-paced environment where scientists, engineers, and product managers work to test and build scalable foundational capabilities, as well as customer facing experiences. You will have the opportunity to innovate and think big within your projects scope, implement optimization services and algorithms, and influence the experiences of millions of customers. We are looking for a results-oriented Applied Scientist with deep knowledge in ML, NLP, Deep Learning, GenAI, and/or large-scale distributed computation. As an Applied Scientist, you will... - Understand use cases across the business and adopt/extend/design/invent solutions/models that are scalable, efficient, and automated for difficult problems that are not well defined - Work closely with fellow scientists and software engineers (at Audible and Amazon) to build and productionize models, deliver novel and highly impactful features - Review models of peers for the purpose of reducing and managing risk to the business, while improving customer experience - Design, develop, and deploy modeling techniques and solutions for Content Understanding, Recommendations, GenAI-based product features, by employing a wide range of methodologies, working from simple to complex - Contribute to initiatives that employ the most recent advances in ML/AI in a fast-paced, experimental environment - Push the boundary of innovation ABOUT AUDIBLE Audible is the leading producer and provider of audio storytelling. We spark listeners’ imaginations, offering immersive, cinematic experiences full of inspiration and insight to enrich our customers daily lives. We are a global company with an entrepreneurial spirit. We are dreamers and inventors who are passionate about the positive impact Audible can make for our customers and our neighbors. This spirit courses throughout Audible, supporting a culture of creativity and inclusion built on our People Principles and our mission to build more equitable communities in the cities we call home.
Applied Scientist II, On Road Experience
IN, KA, Bengaluru
This position is based in Bangalore, India The Last Mile team helps get packages from delivery stations to a customer’s doorstep. To provide new innovations for customers, awe are inventing the next-generation smart delivery operation. We are combining innovative mobile and IoT technologies, data streams (video, vehicle telematics, location, and presence), together with machine learning models and algorithms – all to create solutions that allow us to deliver faster, and with more confidence. Playing a key role in the Last Mile Driver Experience team, as a Applied Scientist you will be responsible for building machine learning models and algorithms in areas including mapping and location, pattern detection in sensor data, and computer vision. Using your research, you will work with your engineering and product management peers to drive designs from ideation through development and into production. You will bring your experience of research for similar products and solutions, preferably in consumer or industrial verticals. This role requires autonomy and an ability to deliver results, often within the ambiguity of building a v1 product. You will need to work efficiently to build the right things with limited guidance, raising the bar to create an amazing experience for our customers.
Applied Scientist, EU INTech Consumer Selection Discovery, NintAI
ES, M, Madrid
Amazon's EU International Technology (EU INTech) organisation is creating new ways for customers to discover products through innovative customer experiences. We are a science-only team within EU INTech, responsible for designing and developing AI/ML science solutions that support business needs across Amazon's global search and discovery experiences. Our mission is to make Amazon navigation easier for customers worldwide. We achieve this through two strategic pillars: making Amazon navigation more visual and improving Amazon navigation with more inspiring discovery tools and narrowing navigation. To support this vision, we build and deploy AI/ML models that surface the most relevant content to hundreds of millions of Amazon customers worldwide. Our team comprises Applied Scientists and we partner with other teams, collaborating with ML Engineers, Software Developers, Product Managers, Technical Product Managers, and UX Designers. We are located in the Madrid Technical Hub. We are looking for Applied Scientists who are passionate about solving highly ambiguous and challenging problems at global scale. This is a hands-on, end-to-end applied science role where you will own the full lifecycle of science solutions — from business problem analysis and science plan design, through development and experimentation, to production deployment. We are looking for AI/ML experts with knowledge on ranking, computer vision, recommendation systems, search, and customer experience design. What makes this role unique: • End-to-end ownership – You will analyse business problems, map them to science plans, and design and develop solutions from ideation to production. We are owners of the full science lifecycle. • Applied science with a research edge – While our focus is on delivering applied science solutions that drive measurable business impact, our team actively pushes the state of the art in areas such as computer vision and Generative AI. • Hands-on execution – We need scientists who thrive in building, experimenting, and shipping. What are we looking for? • A scientist who can independently analyse any business problem and design a rigorous science approach to solve it • Strong hands-on engineering skills — you build and ship, not just theorise • Deep expertise in one or more of: computer vision, generative AI, recommendation systems, ranking, or NLP • Experience taking ML models from research to production at scale • Comfort with ambiguity and the ability to structure complex, undefined problems • A passion for customer-centric innovation and measurable impact • A strong communicator capable to adapt the message from a science audience, to engineering or leadership Key job responsibilities • Analyse complex business problems and translate them into well-defined science plans with clear milestones and success criteria • Design, develop, and deliver ML/AI models end-to-end — from research and prototyping through to production systems at Amazon scale and extending solutions going beyond the state of the art • Work with state-of-the-art models in computer vision, ranking and generative AI to power new customer experiences globally • Own major science challenges for the team, driving solutions from ideation through experimentation to production deployment • Collaborate with a variety of roles and partner teams around the world to deliver integrated solutions • Influence scientific direction and best practices across the team • Maintain high quality standards on team deliverables • Contribute to expanding the state of the art in computer vision, ranking and GenAI through publications and internal knowledge sharing
Applied Scientist, EU INTech Consumer Selection Discovery, NintAI
ES, M, Madrid
Amazon's EU International Technology (EU INTech) organisation is creating new ways for customers to discover products through innovative customer experiences. We are a science-only team within EU INTech, responsible for designing and developing AI/ML science solutions that support business needs across Amazon's global search and discovery experiences. Our mission is to make Amazon navigation easier for customers worldwide. We achieve this through two strategic pillars: making Amazon navigation more visual and improving Amazon navigation with more inspiring discovery tools and narrowing navigation. To support this vision, we build and deploy AI/ML models that surface the most relevant content to hundreds of millions of Amazon customers worldwide. Our team comprises Applied Scientists and we partner with other teams, collaborating with ML Engineers, Software Developers, Product Managers, Technical Product Managers, and UX Designers. We are located in the Madrid Technical Hub. We are looking for Applied Scientists who are passionate about solving highly ambiguous and challenging problems at global scale. This is a hands-on, end-to-end applied science role where you will own the full lifecycle of science solutions — from business problem analysis and science plan design, through development and experimentation, to production deployment. We are looking for AI/ML experts with knowledge on ranking, computer vision, recommendation systems, search, and customer experience design. What makes this role unique: • End-to-end ownership – You will analyse business problems, map them to science plans, and design and develop solutions from ideation to production. We are owners of the full science lifecycle. • Applied science with a research edge – While our focus is on delivering applied science solutions that drive measurable business impact, our team actively pushes the state of the art in areas such as computer vision and Generative AI. • Hands-on execution – We need scientists who thrive in building, experimenting, and shipping. What are we looking for? • A scientist who can independently analyse any business problem and design a rigorous science approach to solve it • Strong hands-on engineering skills — you build and ship, not just theorise • Deep expertise in one or more of: computer vision, generative AI, recommendation systems, ranking, or NLP • Experience taking ML models from research to production at scale • Comfort with ambiguity and the ability to structure complex, undefined problems • A passion for customer-centric innovation and measurable impact • A strong communicator capable to adapt the message from a science audience, to engineering or leadership Key job responsibilities • Analyse complex business problems and translate them into well-defined science plans with clear milestones and success criteria • Design, develop, and deliver ML/AI models end-to-end — from research and prototyping through to production systems at Amazon scale and extending solutions going beyond the state of the art • Work with state-of-the-art models in computer vision, ranking and generative AI to power new customer experiences globally • Own major science challenges for the team, driving solutions from ideation through experimentation to production deployment • Collaborate with a variety of roles and partner teams around the world to deliver integrated solutions • Influence scientific direction and best practices across the team • Maintain high quality standards on team deliverables • Contribute to expanding the state of the art in computer vision, ranking and GenAI through publications and internal knowledge sharing
Senior Applied Scientist, AGI Customization
US, CA, Sunnyvale
The Artificial General Intelligence (AGI) Customization Team is seeking a highly skilled and experienced Applied Scientist to support adoption and enable customization of Amazon Nova. The role focuses on developing state-of-the-art services and tools for model customization, including supervised fine-tuning, reinforcement learning, and knowledge distillation across large language models. As an Applied Scientist, you will play a important role in developing advanced customization capabilities that enable enterprises to build highly performant application-specific models without the need for training models from scratch. Your work will directly impact how companies leverage Amazon Nova models for their specific use cases. Key job responsibilities - Contribute to the development of novel customization techniques including extended post-training, continued pre-training, and advanced knowledge distillation - Collaborate with cross-functional teams to design and implement enterprise-ready tooling for various training techniques on Amazon SageMaker - Design and execute experiments to optimize model accuracy, latency, and cost across different customization approaches (SFT, DPO, PPO) - Develop and enhance preference learning algorithms and training curricula for customer-specific applications - Create robust evaluation frameworks for assessing model performance across different domains and use cases - Contribute to the development of the Responsible AI toolkit, including creating training and evaluation datasets for model alignment - Design and implement secure access mechanisms for early model checkpoints and weights - Communicate technical insights and results to both technical and non-technical stakeholders through presentations and documentation
Applied Scientist II
IN, KA, Bengaluru
Amazon is seeking a passionate and inventive Applied Scientist II with a strong machine learning background to build industry-leading Speech and Language technology. Our mission is to deliver delightful customer experiences by advancing Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), Machine Learning (ML), and Computer Vision (CV). You will work alongside internationally recognized experts to develop novel algorithms and modeling techniques that advance the state-of-the-art in human language technology. Your work will directly impact millions of customers through products and services powered by speech and language technology. You will gain hands-on experience with Amazon's heterogeneous speech, text, and structured data sources, and leverage large-scale computing resources to accelerate advances in spoken language understanding. We are hiring across all areas of human language technology: ASR, Machine Translation (MT), NLU, Text-to-Speech (TTS), Dialog Management, and Computer Vision. We also seek talent experienced in building large-scale, high-performing systems. Key job responsibilities Basic Qualifications PhD or M.Tech in Computer Science, Electrical Engineering, Mathematics, or Physics with specialization in one or more of: speech recognition, natural language processing, machine translation, time series analysis, signal processing, or machine learning 1-2 years of industry or research experience (including internships, co-ops, or post-doctoral work) in applied ML or related areas Proficiency in programming languages such as Python, C/C++, or Java Strong foundation in machine learning fundamentals and statistical modeling Preferred Qualifications Experience building speech recognition, machine translation, or natural language processing systems (e.g., commercial products, government projects, or published research with working prototypes) Hands-on experience with deep learning frameworks (e.g., PyTorch, TensorFlow) Track record of publications in top-tier conferences (e.g., NeurIPS, ICML, ACL, Interspeech, CVPR) Scientific thinking with demonstrated ability to innovate and contribute to advancing the field Solid software development practices and experience shipping production-quality code Strong written and verbal communication skills A day in the life 0
Senior Economist, Decision Science - Devices
US, CA, San Jose
Are you excited about making business decisions using science and data? Are you interested in supporting consumer device concepts from idea inception to launch? Do you want to work on a Science Product team focused on scaling statistics and econometrics with custom tools? If so, this may be the role for you! Amazon.com strives to be Earth's most customer-centric company. The Amazon Devices and Services team focuses on delighting customer by enabling seamless functionality in supplying, entertaining, and managing the home -- and beyond. We seek and hire the world's brightest minds, offering them a fast-paced, technologically-sophisticated, and friendly work environment, where economic theory meets real-world industry. The Decision Science team in Devices owns demand estimates and pricing recommendations of concept devices before customers know they exist. We support devices and services ranging from Echo Frames to Kindle Paperwhite to Blink Video Camera …all prior to launch. We are a cross-functional Product team working to scale Econometrics through Amazon and beyond by incorporating Science into internal facing tools and making it easier for others to do so as well. In this role, you will have input in decision meetings with Amazon senior leadership, which include go/no-go decisions for brand new devices and services and build volume decisions for manufacture prior to receiving any customer signal. You will have direct input to pricing decisions. You will leverage Science and Tools produced by the Decision Science team such as conjoint demand models to produce these recommendations. You will work with Scientists, Economists, Product Managers, and Software Developers to provide meaningful feedback about stakeholder problems to inform business solutions and increase the velocity, quality, and scope behind our recommendations. You will also have the opportunity to work on special projects to both guide the business and advance your own knowledge and understanding of specific topics. Key job responsibilities Applies expertise to develop econometric/machine learning models to measure the demand of devices and the business; Reviews models and results for other scientists, mentors junior scientists; Generates economic insights for the Devices and Services business and work with stakeholders to run the business for effectively; Describes strategic importance of vision inside and outside of team; and, Identifies business opportunities, defines the problem and how to solve it; Engages with senior scientists, business leadership outside Devices and Services to understand interplay between different business units.
2027 Applied Science Intern (Machine Learning, Recommender Systems), Amazon International Machine Learning
AU, VIC, Melbourne
Are you excited about leveraging and extending state-of-the-art Deep Learning, Information Retrieval, Natural Language Processing, Computer Vision algorithms to solve customer problems at the scale of Amazon? As an Applied Scientist Intern, you will be working in the Melbourne office in a fast-paced, cross-disciplinary team of experienced R&D scientists. You will take on complex problems, work on solutions that leverage existing academic and industrial research, and utilize your own out-of-the-box pragmatic thinking. In addition to coming up with novel solutions and prototypes, you may even deliver these to production in customer facing products. Key job responsibilities - Develop novel solutions and build prototypes - Work on complex problems in Deep Learning and Generative AI - Contribute to research that could significantly impact Amazon operations - Collaborate with a diverse team of experts in a fast-paced environment - Present your research findings to both technical and non-technical audiences - Collaborate with scientists on writing and submitting papers to top ML conferences, e.g. NeurIPS, ICML, ICLR, AISTATS, ACL ICCV, CVPR, KDD. Key Opportunities: - Work in a team of ML scientists to solve applied science problems at the scale of Amazon - Access to Amazon services and hardware - Potentially deliver solutions to production in customer-facing applications - Opportunities to be hired full-time after the internship Join us in shaping the future of AI at Amazon. Apply now and turn your research into real-world solutions!
Applied Scientist, Prime Video - Content Localization, Understanding & Enrichment
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video subscriptions such as Apple TV+, HBO Max, Peacock, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video team member, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! Key job responsibilities - Lead research and development of speech and audio generation technology and end-to-end speech-to-speech architecture - Develop audio processing solutions for production environments, including source separation, enhancement, and mixing - Define the research roadmap for your area, identify high-impact problems, and communicate technical direction to senior leadership - Publish research, contribute to the broader scientific community, and bring external advances into production systems - Hire, mentor, and develop applied scientists. Grow the team's capabilities to meet evolving customer and business needs About the team This team's mission is to deeply understand all content and empower all customers with relevant language options, innovative accessibility assists, and rich title-information across all their content-experiences on Prime Video. We create and publish content on-time that's meaningful, accurate, and accessible to every customer globally. We delight our customers by pushing the boundaries of content understanding and enrichment. Through inclusion and innovation, we do the most fulfilling work of our career.
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