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, AWS Automated Reasoning
US, VA, Arlington
Applied Scientists in AWS Automated Reasoning are dedicated to making AWS the best computing service in the world for customers who require advanced and rigorous solutions for automated reasoning, privacy, and sovereignty. Key job responsibilities The successful candidate will: - Solve large or significantly complex problems that require deep knowledge and understanding of your domain and scientific innovation. - Own strategic problem solving, and take the lead on the design, implementation, and delivery for solutions that have a long-term quantifiable impact. - Provide cross-organizational technical influence, increasing productivity and effectiveness by sharing your deep knowledge and experience. - Develop strategic plans to identify fundamentally new solutions for business problems. - Assist in the career development of others, actively mentoring individuals and the community on advanced technical issues. A day in the life This is a unique and rare opportunity to get in early on a fast-growing segment of AWS and help shape the technology, product and the business. You will have a chance to utilize your deep technical experience within a fast moving, start-up environment and make a large business and customer impact. About the team Diverse Experiences Amazon Automated Reasoning 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 Amazon Automated Reasoning? At Amazon, automated reasoning is central to maintaining customer trust and delivering delightful customer experiences. Our organization is responsible for creating and maintaining a high bar for automated reasoning across all of Amazon's products and services. We offer talented automated reasoning professionals the chance to accelerate their careers with opportunities to build experience in a wide variety of areas including cloud, devices, retail, entertainment, healthcare, operations, and physical stores. Inclusive Team Culture In Amazon Automated Reasoning, it's in our nature to learn and be curious. Ongoing DEI events and learning experiences inspire us to continue learning and to embrace our uniqueness. Addressing the toughest automated reasoning challenges requires that we seek out and celebrate a diversity of ideas, perspectives, and voices. Training & 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, training, 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 flexible work hours and arrangements are part of our culture. When we feel supported in the workplace and at home, there's nothing we can't achieve.
Applied Scientist, AWS Identity
US, VA, Arlington
Are you passionate about programming languages, applying formal verification, program analysis, constraint-solving, and/or theorem proving to real world problems? Do you want to create products that help customers? If so, then we have an exciting opportunity for you. In this role, you will interact with internal teams and external customers to understand their requirements. You will apply your knowledge to propose innovative solutions, create software prototypes, and productize prototypes into production systems using software development tools and methodologies. In addition, you will support and scale your solutions to meet the ever growing demand of customer use. Technical Responsibilities: - Interact with various teams to develop an understanding of their security and safety requirements. - Apply the acquired knowledge to build tools find problems, or show the absence of security/safety problems. - Implement these tools through the use of SAT, SMT, and various concepts from programming languages, theorem proving, formal verification and constraint solving. - Perform analysis of the customer systems using tools developed in-house or externally provided - Create software prototypes to verify and validate the devised solutions methodologies; integrate the prototypes into production systems using standard software development tools and methodologies. Leadership Responsibilities: - Can present and defend company-wide technical decisions to the internal technical community and represent the company effectively at technical conferences. - Functional thought leader, sought after for key tech decisions. Can successfully sell ideas to an executive level decision maker. - Mentors and trains the research scientist community on complex technical issues. AWS has the most services and more features within those services, than any other cloud provider–from infrastructure technologies like compute, storage, and databases–to emerging technologies, such as machine learning and artificial intelligence, data lakes and analytics, and Internet of Things. Whether its Identity features such as access management and sign on, cryptography, console, builder & developer tools, and even projects like automating all of our contractual billing systems, AWS Platform is always innovating with the customer in mind. The AWS Platform team sustains over 750 million transactions per second. We have a formal mentor search application that lets you find a mentor that works best for you based on location, job family, job level etc. Your manager can also help you find a mentor or two, because two is better than one. In addition to formal mentors, we work and train together so that we are always learning from one another, and we celebrate and support the career progression of our team members. Key job responsibilities Technical Responsibilities: - Interact with various teams to develop an understanding of their security and safety requirements. - Apply the acquired knowledge to build tools find problems, or show the absence of security/safety problems. - Implement these tools through the use of SAT, SMT, BDDs, and various concepts from programming languages, theorem proving, formal verification and constraint solving. - Perform analysis of the customer systems using tools developed in-house or externally provided - Create software prototypes to verify and validate the devised solutions methodologies; integrate the prototypes into production systems using standard software development tools and methodologies. Leadership Responsibilities: - Can present and defend company-wide technical decisions to the internal technical community and represent the company effectively at technical conferences. - Functional thought leader, sought after for key tech decisions. Can successfully sell ideas to an executive level decision maker. - Mentors and trains the research scientist community on complex technical issues. A day in the life You will be working on cutting edge technology related to formal methods, automated reasoning, automated testing, and adjacent areas. You will work with fellow applied scientists to solve challenging problems that provide value to customers by improving the quality of software. You will have an opportunity to publish your work. 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. AWS Utility Computing (UC) provides product innovations — from foundational services such as Amazon’s Simple Storage Service (S3) and Amazon Elastic Compute Cloud (EC2), to consistently released new product innovations that continue to set AWS’s services and features apart in the industry. As a member of the UC organization, you’ll support the development and management of Compute, Database, Storage, Internet of Things (Iot), Platform, and Productivity Apps services in AWS, including support for customers who require specialized security solutions for their cloud services. 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. 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. 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. 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. About the team The Automated Reasoning in Identity (ARI) team is growing fast. It works on applying automated reasoning techniques to services within AWS's Identity organization, building on initial successes of the Zelkova and Access Analyzer projects. The reach of AR within Identity is growing, with more scientists joining all the time.
Applied Scientist II, Amazon Shipping
IN, HR, Gurugram
Work on ML teams building large-scale forecasting and optimization systems that power Amazon’s global transportation network and directly impact customer experience and cost. As an Applied Scientist II, you will set scientific direction, mentor applied scientists, and partner with engineering and product leaders to deliver production-grade ML solutions at massive scale. Key job responsibilities 1. Lead and grow a high-performing team of Applied Scientists, providing technical guidance, mentorship, and career development. 2. Define and own the scientific vision and roadmap for ML solutions powering large-scale transportation planning and execution. 3. Guide model and system design across a range of techniques, including tree-based models, deep learning (LSTMs, transformers), LLMs, and reinforcement learning. 4. Ensure models are production-ready, scalable, and robust through close partnership with stakeholders. Partner with Product, Operations, and Engineering leaders to enable proactive decision-making and corrective actions. 5. Own end-to-end business metrics, directly influencing customer experience, cost optimization, and network reliability. 6. Help contribute to the broader ML community through publications, conference submissions, and internal knowledge sharing. A day in the life Your day includes reviewing model performance and business metrics, guiding technical design and experimentation, mentoring scientists, and driving roadmap execution. You’ll balance near-term delivery with long-term innovation while ensuring solutions are robust, interpretable, and scalable. Ultimately, your work helps improve delivery reliability, reduce costs, and enhance the customer experience at massive scale.
Member of Technical Staff, Artificial General Intelligence
US, CA, Sunnyvale
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will support the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will support the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
Economist, Amazon Customer Service
US, WA, Seattle
Amazon Customer Service (CS) Data Intelligence builds the data and Artificial Intelligence (AI) foundations for CS to ensure Amazon delivers the best customer service possible. CS Economics sits within CS DI and contributes to the CS knowledge base and decision frameworks. CS Economics seeks economists to apply economic methods to solve business problems. The ideal candidate will work with engineers and applied scientists to design models that leverage large scale and unstructured data, design scalable agents for non-tech CS partners to understand the impact of their actions, and propose mechanism designs to robustly match customers to our services. CS Economics is looking for optimistic critical-thinkers who combine a strong technical economic toolbox with a desire to learn from other disciplines, and who know how to execute and deliver on big ideas as part of an interdisciplinary technical team. Ideal candidates enjoy working in a team setting with individuals from diverse disciplines and backgrounds. They will work with teammates to develop scientific models and conduct data analysis, modeling, and experimentation that is necessary for estimating and validating models. They will work closely with engineering teams to develop scalable data resources to support rapid insights, and take successful models and findings into production as new products and services. They will be customer-centric and will communicate scientific approaches and findings to business leaders, listening to and incorporate their feedback, and delivering successful scientific solutions. Key job responsibilities - Design and conduct rigorous evaluations of CS actions - Develop experiments to evaluate product launches - Communicate complex findings to business stakeholders in clear, actionable terms - Work with engineering teams to develop scalable tools that automate and streamline evaluation processes A day in the life Work with teammates to apply economic methods to business problems, e.g., identify the appropriate research question and identification strategy, write code to estimate heterogeneous treatment effects or conduct experiment analysis, write and present a document with findings to business leaders. We collaborate with partner teams within and outside of CS throughout the process, from understanding their challenges, to developing a research agenda that will address those challenges, to help them implement solutions. About the team Amazon Customer Service (CS) Economics provides estimates and measures of the causal impact of CS actions on costs and benefits. We build agents and guide leadership to establish processes to scale valid experimentation, causal inference, and mechanism design.
Applied Scientist, Prime Video Personalization and Discovery Science, Prime Video - Personalization and Discovery Science
US, CA, Sunnyvale
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 add-on subscriptions such as Apple TV+, Max, 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 technologist, 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 Develop foundation models for content understanding using state-of-the-art deep learning and multimodal learning techniques to analyze video and text Build time sequence foundation models to understand and predict customer behavior patterns and viewing trajectories Work closely with engineers and product managers to design, implement and launch solutions end-to-end across various Prime Video experiences Design and conduct offline and online (A/B) experiments to evaluate proposed solutions based on in-depth data analyses Effectively communicate technical and non-technical ideas with teammates and stakeholders Stay up-to-date with advancements and the latest modeling techniques in foundation models, multimodal learning, and time series analysis Publish your research findings in top conferences and journals A day in the life We're using advanced approaches such as foundation models to connect information about our videos and customers from a variety of information sources, acquiring and processing data sets on a scale that only a few companies in the world can match. This will enable us to recommend titles effectively, even when we don't have a large behavioral signal (to tackle the cold-start title problem). It will also allow us to find our customer's niche interests, helping them discover groups of titles that they didn't even know existed. We are looking for creative & customer obsessed machine learning scientists who can apply the latest research, state of the art algorithms and ML to build highly scalable page personalization solutions. You'll be a research leader in the space and a hands-on ML practitioner, guiding and collaborating with talented teams of engineers and scientists and senior leaders in the Prime Video organization. You will also have the opportunity to publish your research at internal and external conferences. About the team Prime Video Recommendation Science team owns science solution to power recommendation and personalization experience on various Prime Video surfaces and devices. We work closely with the engineering teams to launch our solutions in production.
Senior Applied Scientist, Special Projects
US, WA, Seattle
Innovators wanted! Are you an entrepreneur? A builder? A dreamer? This role is part of an Amazon Special Projects team that takes the company’s Think Big leadership principle to the limits. If you’re interested in innovating at scale to address big challenges in the world, this is the team for you. As a Senior Applied Scientist on our team, you will focus on building state-of-the-art ML models for healthcare. Our team rewards curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the forefront of both academic and applied research in this product area, you have the opportunity to work together with a diverse and talented team of scientists, engineers, and product managers and collaborate with other teams. This role offers a unique opportunity to work on projects that could fundamentally transform healthcare outcomes. Key job responsibilities In this role, you will: • Design and implement novel AI/ML solutions for complex healthcare challenges • Drive advancements in machine learning and data science • Balance theoretical knowledge with practical implementation • Work closely with customers and partners to understand their requirements • Navigate ambiguity and create clarity in early-stage product development • Collaborate with cross-functional teams while fostering innovation in a collaborative work environment to deliver impactful solutions • Establish best practices for ML experimentation, evaluation, development and deployment • Partner with leadership to define roadmap and strategic initiatives You’ll need a strong background in AI/ML, proven leadership skills, and the ability to translate complex concepts into actionable plans. You’ll also need to effectively translate research findings into practical solutions. A day in the life You will solve real-world problems by getting and analyzing large amounts of data, generate insights and opportunities, design simulations and experiments, and develop statistical and ML models. The team is driven by business needs, which requires collaboration with other Scientists, Engineers, and Product Managers across the Special Projects organization. You will prepare written and verbal presentations to share insights to audiences of varying levels of technical sophistication. About the team We represent Amazon's ambitious vision to solve the world's most pressing challenges. We are exploring new approaches to enhance research practices in the healthcare space, leveraging Amazon's scale and technological expertise. We operate with the agility of a startup while backed by Amazon's resources and operational excellence. We're looking for builders who are excited about working on ambitious, undefined problems and are comfortable with ambiguity.
Applied Scientist, Sponsored Products and Brands
US, CA, Palo Alto
About Sponsored Products and Brands The Sponsored Products and Brands (SPB) 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 our team SPB Ad Response Prediction team is your choice, if you want to join a highly motivated, collaborative, and fun-loving team with a strong entrepreneurial spirit and bias for action. We are seeking an experienced and motivated Applied Scientist with machine learning engineering background who loves to innovate at the intersection of customer experience, deep learning, and high-scale machine learning systems. We are looking for a talented Applied Scientist with a strong background in machine learning engineering to join our team and help us grow the business. In this role, you will partner with a team of engineers and scientists to build advanced machine learning models and infrastructure, from training to inference, including emerging LLM-based systems, that deliver highly relevant ads to shoppers across all Amazon platforms and surfaces worldwide. Key job responsibilities As an Applied Scientist, you will: * Develop scalable and effective machine learning models and optimization strategies to solve business problems. * Conduct research on new machine learning modeling to optimize all aspects of Sponsored Products business. * Enhance the scalability, automation, and efficiency of large-scale training and real-time inference systems. * Pioneer the development of LLM inference infrastructure to support next-generation GenAI workloads at Amazon Ads scale.
Applied Scientist, Amazon Music - Search Science
US, CA, Sunnyvale
Amazon Music is an immersive audio entertainment service that deepens connections between fans, artists, and creators. From personalized music playlists to exclusive podcasts, concert livestreams to artist merch, Amazon Music is innovating at some of the most exciting intersections of music and culture. We offer experiences that serve all listeners with our different tiers of service: Prime members get access to all the music in shuffle mode, and top ad-free podcasts, included with their membership; customers can upgrade to Amazon Music Unlimited for unlimited, on-demand access to 100 million songs, including millions in HD, Ultra HD, and spatial audio; and anyone can listen for free by downloading the Amazon Music app or via Alexa-enabled devices. Join us for the opportunity to influence how Amazon Music engages fans, artists, and creators on a global scale. Amazon Music - Search Science team is seeking an experienced Applied Scientist who will join a team of experts in the field of machine learning, and work together to break new ground in the world of understanding and classifying different forms of music, and creating interactive experiences to help users find the music they are in the mood for. We work on machine learning problems for music classification, recommender systems, dialogue systems, NLP, and music information retrieval. You'll work in a collaborative environment where you can pursue applied research, with many peta-bytes of data, work on problems that haven’t been solved before, quickly implement and deploy your algorithmic ideas at scale, understand whether they succeed via statistically relevant experiments across millions of customers, and publish your research. You'll see the work you do directly improve the experience of Amazon Music customers on Alexa/Echo, mobile, and web. Key job responsibilities - Use machine learning, deep learning, LLMs and Agentic AI techniques to create scalable solutions for business problems - Analyze and extract relevant information from large amounts of Amazon's data to help automate and optimize key processes - Design, development and evaluation of AI models for predictive learning - Work closely with software engineering teams to drive model implementations and new feature creations - Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation - Research and implement novel machine learning and statistical approaches About the team Everyone on our team has a meaningful impact on product features, new directions in music streaming, and customer engagement. We are looking for new team members across a variety of job functions including software engineering/development, marketing, design, ops and more. Come join us as we make history by launching exciting new projects in the coming year.Our team is focused on building a personalized, curated, and seamless music experience. We want to help our customers discover up-and-coming artists, while also having access to their favorite established musicians. We build systems that are distributed on a large scale, spanning our music apps, web player, and voice-forward audio engagement on mobile and Amazon Echo devices, powered by Alexa to support our customer base. Amazon Music offerings are available in countries around the world, and our applications support our mission of delivering music to customers in new and exciting ways that enhance their day-to-day lives.
Applied Scientist II, Data Intelligence and Governance
US, CA, Sunnyvale
We are seeking an Applied Scientist II to work on development of an AI-based data intelligence and classification platform that will redefine how security and privacy assessments and enforcement are conducted at scale. This mission-critical platform will leverage AI-driven autonomous agents to conduct proactive, intelligent security operations across the company. The platform will integrate deeply with internal security, privacy, engineering, and cloud-native tools to provide self-serve, automated insights, verifications, and enforcement mechanisms. This role requires strong technical expertise in AI/ML, LLMs, and distributed cloud infrastructure, as well as thought leadership to drive alignment across multiple teams, customers, and business units. This is an opportunity to shape the future of AI-driven security and privacy assurance at an enterprise scale, defining standards, influencing company-wide security posture, and leading technical innovation at the highest level. Key job responsibilities * Architect and define the next-generation data classification and search matching platform, leading the technical strategy for AI-driven security automation across applied science and engineering teams * Build on multi-agent LLM framework, and influence your organizations in adopting the promising approaches * Develop a highly scalable, traditional ML-based as well as LLM-based intelligent security agent framework that enables internal teams to automate processing of structured and unstructured data * Combine depth and breadth of domain expertise and provide technical leadership to the entire team while also doing hands-on work by diving deep into details to diagnose complex system performance problems. About the team The Data Categorization team helps Amazonians understand their data and govern it at scale and ensures experiences delivered by Amazon to our customers uphold our high security and privacy standards. The science team harnesses AI to strengthen Amazon’s privacy and security posture more efficiently and effectively.
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