Social
Conversational AI

Amazon releases 51-language dataset for language understanding

MASSIVE dataset and Massively Multilingual NLU (MMNLU-22) competition and workshop will help researchers scale natural-language-understanding technology to every language on Earth.

By Jack G. M. FitzGerald
April 20, 2022
6 min read
Share

Imagine that all people around the world could use voice AI systems such as Alexa in their native tongues.

Multilingual Alexa.png
The MASSIVE dataset is a step toward the creation of multilingual natural-language-understanding models that can generalize easily to new languages.

One promising approach to realizing this vision is massively multilingual natural-language understanding (MMNLU), a paradigm in which a single machine learning model can parse and understand inputs from many typologically diverse languages. By learning a shared data representation that spans languages, the model can transfer knowledge from languages with abundant training data to those in which training data is scarce.

Today we are pleased to make three announcements related to MMNLU.

First, we are releasing a new dataset called MASSIVE, which is composed of one million labeled utterances spanning 51 languages, along with open-source code, which provides examples of how to perform massively multilingual NLU modeling and allows practitioners to re-create baseline results for intent classification and slot filling that are presented in our paper..

polyglot_diagram.png
Related content
English-language Alexa voice learns to speak Spanish
Neural text-to-speech enables new multilingual model to use the same voice for Spanish and English responses.

Second, we are launching a new competition using the MASSIVE dataset called Massively Multilingual NLU 2022 (MMNLU-22).

And third, we will cohost a workshop at EMNLP 2022 in Abu Dhabi and online, also called Massively Multilingual NLU 2022, which will highlight the results from the competition and include presentations from invited speakers and oral and poster sessions from submitted papers on multilingual natural-language processing (NLP).

“We are very excited to share this large multilingual dataset with the worldwide language research community,” says Prem Natarajan, vice president of Alexa AI Natural Understanding. “We hope that this dataset will enable researchers across the world to drive new advances in multilingual language understanding that expand the availability and reach of conversational-AI technologies.”

The MASSIVE dataset

MASSIVE is a parallel dataset, meaning that every utterance is given in all 51 languages. This enables models to learn shared representations of utterances with the same intents, regardless of language, facilitating cross-linguistic training on natural-language-understanding (NLU) tasks. It also allows for adaptation to other NLP tasks such as machine translation, multilingual paraphrasing, new linguistic analyses of imperative morphologies, and more.

The architecture of our slot-filling and intent classification model
Related content
Cross-lingual transfer learning for multilingual voice agents
In experiments, multilingual models outperform monolingual models.

NLU — a subdiscipline of NLP — is a machine's ability to understand the meaning of a text and identify the relevant entities. For instance, given the utterance “What is the temperature in New York?”, an NLU model might classify the intent as “weather_query” and recognize relevant entities as “weather_descriptor: temperature” and “place_name: new york.”

Related links

Our particular focus is on NLU as a component of spoken-language understanding (SLU), in which audio is converted to text before NLU is performed. Although SLU-based virtual assistants like Alexa have made major capability advances in the past decade, academic and industrial NLU efforts worldwide are still limited to a small subset of the world's 7,000+ languages. One difficulty in creating massively multilingual NLU models is the lack of labeled data for training and evaluation — particularly data that is realistic for a given task and natural for a given language. High naturalness typically requires human vetting, which is often costly.

MASSIVE — Multilingual Amazon SLURP (SLU resource package) for Slot Filling, Intent Classification, and Virtual-Assistant Evaluation — contains one million realistic, parallel, labeled virtual-assistant text utterances spanning 51 languages, 18 domains, 60 intents, and 55 slots. MASSIVE was created by tasking professional translators to localize or translate the English-only SLURP dataset into 50 typologically diverse languages from 29 genera, including low-resource languages.

Name

# Lang

Utt/Lang

Domains

Intents

Slots

MASSIVE

51

19,521

18

60

55

SLURP (Bastianelli et al., 2020)

1

16,521

18

60

55

NLU Evaluation Data (Liu et al., 2019)

1

25,716

18

54

56

Airline Travel Information System (ATIS) (Price, 1990)

1

5,871

1

26

129

ATIS with Hindi and Turkish (Upadhyay et al., 2018)

3

1,315-5,871

1

26

129

MultiATIS++ (Xu et al., 2020)

9

1,422-5,897

1

21-26

99-140

Snips (Coucke et al., 2018)

1

14,484

-

7

53

Snips with French (Saade et al., 2019)

2

4,818

2

14-15

11-12

Task Oriented Parsing (TOP) (Gupta et al., 2018)

1

44,873

2

25

36

Multilingual Task-Oriented Semantic Parsing
(MTOP) (Li et al., 2021)

6

15,195-22,288

11

104-113

72-75

Cross-Lingual Multilingual Task Oriented Dialog
(Schuster et al., 2019)

3

5,083-43,323

3

12

11

Microsoft Dialog Challenge (Li et al., 2018)

1

38,276

3

11

29

Fluent Speech Commands (FSC)
(Lugosch et al., 2019)

1

30,043

-

31

-

Chinese Audio-Textual Spoken Language
Understanding (CATSLU) (Zhu et al., 2019)

1

16,258

4

-

94

We have released a paper describing the dataset and presenting baseline modeling results on XLM-R and mT5 models. Tools for the dataset, as well as the modeling code used for our baseline results, are available in our Github repository. MASSIVE is licensed under the CC BY 4.0 license, encouraging its broadest possible use across academia and industry.

MMNLU competition and workshop

The MASSIVE leaderboard and the Massively Multilingual NLU 2022 competition, hosted on eval.ai, are composed of two tasks. In the first, called MMNLU-22-Full, each competitor trains and tests a single model on all 51 languages of the full MASSIVE dataset. In the second task, called MMNLU-22-ZeroShot, each competitor fine-tunes a pretrained model only with English-labeled data and tests it on all 50 non-English languages.

Locale-agnostic_architecture.png._CB462220682_.png
Related content
Adapting Alexa to regional language variations
As Alexa expands into new countries, she usually has to be trained on new languages. But sometimes, she has to be re-trained on languages she’s already learned. British English, American English, and Indian English, for instance, are different enough that for each of them, we trained a new machine learning model from scratch.

This assesses the model’s ability to generalize to new languages, an important consideration given the number of languages around the world for which there is little-to-no labeled data. Zero-shot learning is a key technology for scaling NLU technology to many more low-resource languages worldwide.

The permanent MASSIVE leaderboard has been launched, and on July 25 the Massively Multilingual NLU 2022 evaluation split will be released. Participants will then have until August 8 to perform inference on the evaluation set and submit their predictions, which will be used to determine the winners. Winners will be invited to give an oral presentation at the Massively Multilingual NLU 2022 workshop.

The Massively Multilingual NLU 2022 workshop is collocated with EMNLP 2022 and will take place on either December 7 or 8, both in person in Abu Dhabi and online. Paper submissions spanning the breadth of multilingualism in NLU are sought, and the first call for papers will be released soon. The workshop will feature speakers on various topics related to multilingualism and NLU, as well as talks from the top performers from the MMNLU-22 competition.

CLTL_model.png._CB449094769_.png
Related content
Improving cross-lingual transfer learning by filtering training data
In a paper we’re presenting at this year’s Conference on Empirical Methods in Natural Language Processing, we describe experiments with a new data selection technique.

Let’s scale natural-language-understanding technology to every language on Earth. Come build with us!

Acknowledgments

Christopher Hench, Charith Peris, Scott Mackie, Kay Rottmann, Ana Sanchez, Aaron Nash, Liam Urbach, Vishesh Kakarala, Richa Singh, Swetha Ranganath, Laurie Crist, Misha Britan, Wouter Leeuwis, Gokhan Tur, and Prem Natarajan for core dataset contributions; Andrew Turner for product and program management; Anna-Karin Johansson for vendor management; Saleh Soltan for text-to-text modeling discussions; Anne Yoder, Zheng Xie, Adeetee Bhide, Misa Sunaga, Trang Doan, and Satyam Dwivedi for program management and language expertise; Wayne Blossom, Brendan Egan, Columbine Marshall, Todd Tieuli, and Augusta Niles for creating the hidden evaluation split of the dataset; Jack FitzGerald, Kay Rottmann, Julia Hirschberg, Anna Rumshisky, and Mohit Bansal for workshop organization; and Charith Peris and Jack FitzGerald for leaderboard and competition setup.

Research areas
Tags
About the Author
Jack G. M. FitzGerald
Jack G. M. FitzGerald is a senior applied scientist in the Artificial General Intelligence (AGI) organization at Amazon and has a background in machine learning, physics, and tech leadership. He currently focuses on large-language-model pretraining and adaptation, multilingual modeling, optimized distributed training, and efficient modeling operations.

Related content

  • TextToSpeech-16x9.gif
    Improving quality and robustness in LLM-based text-to-speech systems
    Ammar Abbas
    April 1, 2026
    Low-rank adaptation, data augmentation, and chain-of-thought reasoning are among the techniques enabling accent-free polyglot outputs, improved expressiveness, and reliable synthesis.
    Conversational AI
  • PortableReasoning-Hero-16x9.png
    Portable reasoning: Releasing text-bound intelligence into agentic interaction
    Meiqi Sun
    April 20, 2026
    Large language models today can solve algebra, pass academic benchmarks, and generate highly structured chain-of-thought explanations. In text-only settings, they often feel startlingly intelligent — methodical, articulate, even strategic. But place those models inside an interactive environment — ask them to click buttons, scroll pages, fill out forms, and submit answers — and their behavior changes. Their careful reasoning falters. They guess where they once deduced. They adhere to templates and produce limited procedural narration: stating what they see and what they will click next, without first forming a structured plan and acting in accordance with plan. It’s as if part of their intelligence has quietly gone offline the moment the cursor appears.
    Machine learning
  • EvolvingBenchmark_16x9.jpg
    Ground truth is a process, not a dataset
    Venkatesh Saligrama
    June 3, 2026
    Automatically fact-checking long, AI-generated research reports poses new challenges — including benchmarking.
    Machine learning

Work with us

See more jobs See more jobs
Applied Scientist II, RBS Tech
IN, KA, Bengaluru
RBS (Retail Business Services) Tech team works towards enhancing the customer experience (CX) and their trust in product data by providing technologies to find and fix Amazon CX defects at scale. Our platforms help in improving the CX in all phases of customer journey, including selection, discoverability & fulfilment, buying experience and post-buying experience (product quality and customer returns). The team also develops GenAI platforms for automation of Amazon Stores Operations. As a Sciences team in RBS Tech, we focus on foundational ML research and develop scalable state-of-the-art ML solutions to solve the problems covering customer experience (CX) and Selling partner experience (SPX). We work to solve problems related to multi-modal understanding (text and images), task automation through multi-modal LLM Agents, supervised and unsupervised techniques, multi-task learning, multi-label classification, aspect and topic extraction for Customer Anecdote Mining, image and text similarity and retrieval using NLP and Computer Vision for product groupings and identifying duplicate listings in product search results. Key job responsibilities As an Applied Scientist, you will be responsible to design and deploy scalable GenAI, NLP and Computer Vision solutions that will impact the content visible to millions of customer and solve key customer experience issues. You will develop novel LLM, deep learning and statistical techniques for task automation, text processing, image processing, pattern recognition, and anomaly detection problems. You will define the research and experiments strategy with an iterative execution approach to develop AI/ML models and progressively improve the results over time. You will partner with business and engineering teams to identify and solve large and significantly complex problems that require scientific innovation. You will help the team leverage your expertise, by coaching and mentoring. You will contribute to the professional development of colleagues, improving their technical knowledge and the engineering practices. You will independently as well as guide team to file for patents and/or publish research work where opportunities arise. The RBS org deals with problems that are directly related to the selling partners and end customers and the ML team drives resolution to organization level problems. Therefore, the Applied Scientist role will impact the large product strategy, identifies new business opportunities and provides strategic direction which is very exciting.
Research Scientist, Fauna
US, NY, New York
We are seeking a Human-Robot Interaction (HRI) Research Scientist to develop cutting-edge interactions that make robots feel alive, personal, and fun. In this role, you will focus on verbal and non-verbal conversational systems, social dynamics, memory, and long-term relationship formation between robots, their environments, and the people they interact with. Your contributions will be essential in advancing robotics by enabling expressive, socially intelligent, and trustworthy interactions between robots and humans.
Research Scientist, Mobile Manipulation Robotics (I/O)
US, MA, North Reading
Amazon Robotics is transforming warehouse automation through edge AI and machine learning applied to real-world robotics challenges. We're seeking a Research Scientist to advance our mobile manipulation capabilities by developing novel learning-based approaches that enable robots to navigate and manipulate objects in dynamic fulfillment environments. This role offers the opportunity to conduct original research and translate state-of-the-art findings into production systems operating at Amazon's unprecedented scale. Key job responsibilities Research and Algorithm Development: Formulate novel research problems in robot learning and manipulation, design new model architectures, validate hypotheses through rigorous experimentation, and advance the state of the art in learning-based robotics. Data Strategy and Pipeline Design: Define data requirements for research initiatives, design scalable collection and curation strategies, establish governance and provenance standards, and build reusable pipelines ensuring data quality and reproducibility. Experimentation and Scientific Validation: Design and execute experiments in simulation and real-world embodiments, develop evaluation methodologies and benchmarks, perform ablation studies and statistical analyses, and iterate systematically to advance model performance. Prototyping and Research Infrastructure: Develop clean, well-documented research codebases, build experimentation frameworks and evaluation tooling, contribute to shared training infrastructure, and implement interfaces for broader robotics integration. Scientific Leadership and Publication: Drive an independent research agenda aligned with team objectives, publish at top-tier venues (e.g., RSS, CoRL, ICRA, NeurIPS), identify research gaps through literature reviews, and present findings via technical reports and talks. Cross-Functional Collaboration: Partner with scientists, engineers, and leaders across teams to translate research into deployable solutions, mentor junior researchers, contribute to the team's scientific culture, and support integration with robotics hardware teams. A day in the life If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply! About the team Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart, collaborative team of enthusiastic doers that work passionately to apply innovative advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even image yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun!
Sr. Applied Scientist, DemandTech - AdDelivery, Experience and Measurement
US, NY, New York
Want to work on building a Amazon Ads billion dollar business, innovate on a new product, and have a positive impact on millions of views while working with industry-leading technologies? We're growing a team to support the Sponsored Ads business that powers the advertising experience for millions of viewers and advertisers daily. Amazon is investing heavily in building a world-class advertising business and developing a collection of self-service performance advertising products that drive discovery and sales. We deliver billions of ad impressions and millions of clicks daily and are constantly challenging ourselves to create world-class products and an unparalleled shopping experience for our hundreds of millions of customers worldwide. Key job responsibilities We are building the next-gen smart ads campaign. At its core is an Intelligence Flywheel — an architecture where every component's output is designed to train models that improve every other component. The Model Layer that is meant to power every capability currently has no dedicated science ownership. As the Senior Applied Scientist on this team, you own the science that makes the flywheel turn. You will turn static, threshold-based logic into self-improving, closed-loop intelligence, and define the decision policies that let the system act autonomously with advertiser trust. Concretely, you will: * Build predictive issue-detection models that identify under-delivery, over-delivery, and performance degradation from campaign signals before they materially impact advertisers. * Design the intervention-selection policy — which autonomous action to take — framed as a contextual bandit: choose, observe, update. Engineers implement action execution; you define the policy that selects actions. * Establish causal attribution for autonomous optimization, separating the effect of our interventions from organic performance change, so improvements can be attributed and advertiser trust in autonomy can be earned. * Integrate and adapt cross-model signals. Combine creative-quality, product-relevance, and budget signals into a unified advertiser-intelligence picture, and adapt general-purpose partner models to our product reality via fine-tuning, re-ranking, or thin adaptation layers. * Close recommendation and grading feedback loops — define reward schemas for accept/reject and performance-vs-baseline signals, correlate creative-quality scores with real campaign outcomes, and feed empirical findings back to both our product and partner science teams. You will work backwards from ambiguous business problems, set the science roadmap for the Model Layer, and partner closely with the team's software engineers — who own the services, pipelines, and execution infrastructure — so that model artifacts you produce are deployed and served in production. This is a high-leverage, high-autonomy role: your outputs are consumed by multiple engineering workstreams at once, and you set the abstractions the team builds on. About the team We are focused on goal-oriented, AI powered workflows that help advertisers achieve their marketing objectives. We collect campaign goals, surface relevant data at key decision points, and provide reporting that validates decision-making. Our product suite guides advertisers in building campaigns with optimal targeting, creative formats, inventory, and bid models that are highly likely to hit their goals — reducing the need for manual intervention.
Applied Scientist, Catalog System Services Science
US, WA, Seattle
At Amazon Selection and Catalog Systems (ASCS), our mission is to power the online buying experience for customers worldwide so they can find, discover, and buy any product they want. We innovate on behalf of our customers to ensure uniqueness and consistency of product identity and to infer relationships between products in Amazon Catalog to drive the selection gateway for the search and browse experiences on the website. We're solving a fundamental AI challenge: establishing product relevant information at unprecedented scale with Frontier Models and Agents. The scale is staggering: billions of products, petabytes of multimodal data, millions of sellers, dozens of languages, and infinite product diversity ranging from electronics to groceries to digital content. The research challenges are immense. GenAI and VLMs hold transformative promise for catalog understanding, but we operate where traditional methods fail: ambiguous problem spaces, incomplete and noisy data, inherent uncertainty, reasoning across both images and textual data, and explaining decisions at scale. Enriching product information requires sophisticated models that reason across text, images, and structured data, all while maintaining accuracy and trust for high-stakes business decisions affecting millions of customers daily. Amazon's Catalog System Services Science team is looking for an innovative and customer-focused applied scientist to help us make the world's best product catalog even better. In this role, you will partner with technology and business leaders to build new state-of-the-art algorithms, models, and services. You will pioneer advanced GenAI solutions that power next-generation agentic shopping experiences, working in a collaborative environment where you can experiment with massive data from the world's largest product catalog, tackle problems at the frontier of AI research, rapidly implement and deploy your algorithmic ideas at scale, across millions of customers. Key job responsibilities - Formulate novel research problems at the intersection of GenAI, multimodal learning, and large-scale information retrieval. In essence, translating ambiguous business challenges into tractable scientific frameworks - Design and implement leading models leveraging frontier models, and agentic architectures to enrich catalog information at billion-product scale - Pioneer explainable AI methodologies that balance model performance with scalability requirements for production systems impacting millions of daily customer decisions - Own end-to-end ML pipelines from research ideation to production deployment, processing petabytes of multimodal data with rigorous evaluation frameworks - Represent the team in the broader science community - publishing findings, delivering tech talks, and staying at the forefront of GenAI, VLM, and agentic system research
Applied Scientist, Customer360
US, WA, Seattle
What happens when you give AI the ability to remember? Not cached responses — real structured memory that compounds over time and transfers across contexts. We're building the science behind this, and we need researchers who want to own the problem end-to-end. This is a founding role on a new team. You won't inherit models or maintain someone else's pipeline. You'll define the research direction, run experiments at scale, and ship what works directly to production. Key job responsibilities As an Applied Scientist in our team, you will be responsible for the research, design, and development of new AI technologies for knowledge acquisition and retrieval. You will adopt or invent new machine learning and analytical techniques in the realm of information retrieval, knowledge representation, and large language models. Specific responsibilities include: 1. Design and implement novel approaches to knowledge extraction from heterogeneous, unstructured data sources at organizational scale. 2. Build retrieval systems that match intent to relevant knowledge across domains — solving the "right memory at the right time" problem. 3. Own the quality of memory generation: what to capture, how to structure it, when to surface it, and when to let it decay. 4. Run large-scale experiments using Amazon's compute infrastructure and massive real-world datasets. 5. Develop evaluation frameworks for a system where "quality" means something new — right knowledge, right context, right confidence level. 6. Collaborate with engineers to move from research prototype to production system in weeks, not quarters. 7. Invent new approaches to temporal knowledge management — how memories age, conflict, and compound over time. 8. Publish and patent novel approaches to knowledge acquisition and retrieval at top-tier venues. A day in the life You will solve real-world problems by getting and analyzing large amounts of data, generate insights and opportunities, execute 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 organization. You get to influence stakeholders with clear communication skills. You innovate on behalf of the customer and strategically build features. You will mentor junior members and help them grow. About the team We're a new team within Personalization, focused on a different kind of recommendation: not "what product should this customer see" but "what knowledge should this AI use right now." Same scale, same rigor, entirely new problem space. The science is at the intersection of information retrieval, knowledge representation, and LLM reasoning — and the right approach hasn't been established yet. The team values innovation and offers a safe place to try, fail, and learn while fostering a culture of continuous improvement. Everyone is a leader and owner for everything we do as a team. We offer creative space with an entrepreneurial work environment focusing on customer obsession.
Applied Scientist I, Amazon Shipping
IN, HR, Gurugram
Building large-scale forecasting and optimization systems that power Amazon’s global transportation network and directly impact customer experience and cost. Key job responsibilities 1. Guide model and system design across a range of techniques, including tree-based models, deep learning (LSTMs, transformers), LLMs, and reinforcement learning. 2. Ensure models are production-ready, scalable, and robust through close partnership with stakeholders. 3. Partner with Product, Operations, and Engineering leaders to enable proactive decision-making and corrective actions. 4 Own end-to-end business metrics, directly influencing customer experience, cost optimization, and network reliability. 5. Help contribute to the broader ML community through publications, conference submissions, and internal knowledge sharing.
Applied Scientist, Prime Video - Content Reasoning, Enrichment & Localization
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!
Senior Applied Scientist, Real-Time Conversational AI , AGI
US, CA, Sunnyvale
We are looking for a Senior Applied Scientist to help drive the research and development of real-time multimodal conversational AI. You will contribute across two focus areas: advancing foundation models for speech and audio, and building the post-training systems (reward modeling, reinforcement learning) that shape natural, human-like conversational behavior. You will own a significant research area and contribute across the full model lifecycle — from pre-training and architecture design through post-training alignment and real-time deployment. You will work at the frontier of what’s possible in conversational AI, with the compute, data, and runway to pursue problems that few teams in the world have the resources to tackle. As a Senior Scientist, you will drive the technical execution of your research area, contribute to the team’s roadmap, and work closely with inference engineers to ensure your models are designed for real-time production deployment. Key job responsibilities What You’ll Do Foundation Model Scaling - Help build and train large-scale multimodal foundation models for real-time speech and audio generation, from architecture design through production-scale training - Advance the scaling and efficiency of conversational models, including the relationship between data, model size, and real-time performance - Design model architectures informed by hardware constraints and inference requirements, working with inference engineers to ensure models are servable from inception - Develop training methodologies for multimodal models that jointly process and generate speech, language, and audio in real-time streaming contexts - Contribute to the state of the art on efficient architectures and training methods for conversational AI at scale Post-Training & Reinforcement Learning - Design and build reward models and reward functions for speech systems — capturing naturalness, fluency, conversational quality, and real-time responsiveness - Develop and apply reinforcement learning methods to shape conversational behavior — teaching models natural timing, responsiveness, and fluid interaction - Build parts of the post-training pipeline from SFT through RL alignment, optimized for real-time multimodal outputs rather than text-only generation - Design evaluation frameworks that capture the quality dimensions unique to real-time conversation (latency sensitivity, audio quality, prosody, interaction naturalness) Real-Time Perception & Generation - Advance the team’s capabilities in real-time perception — the ability of the model to process incoming audio/speech while simultaneously generating responses - Develop techniques for natural interactive systems where the model handles concurrent input and output with human-like timing - Work at the intersection of model architecture and production constraints to ensure multimodal capabilities function within hard real-time latency budgets
Applied Scientist, SCOT FO - SnT
ES, B, Barcelona
How does Amazon decide which fulfillment center ships your order, which truck carries it, and how to keep promises across hundreds of millions of packages daily? How does it decide how many trucks and how much labor are required to ship orders across the network? SCOT Fulfillment Optimization (FO) owns the optimization and forecasting science behind these decisions. We are seeking Applied Scientists to join the FO Science & Tech team in Barcelona (alternatively: Luxembourg or London) with a strong academic background in optimization, machine learning, and/or time-series forecasting. • You will design and build state-of-the-art machine learning and optimization models that power Amazon's fulfillment decisions at an unprecedented scale across two core scientific pillars: • Large-Scale Optimization and Planning: Designing planning systems for order assignment and resource utilization, while balancing multi-objective cost-speed tradeoffs to enable controllers to steer millions of shipments per hour optimally. • Demand Forecasting & Predictive ML: Developing time-series forecasts for customer demand, incorporating contextual information (weather, sales, order properties), and modeling uncertainty for core planning systems. Basic qualifications • PhD in Operations Research, Applied Mathematics, Computer Science, or related field (or equivalent experience) • Strong programming skills (Python preferred; experience with optimization solvers a plus) • Research experience in one or more: • Large-scale mathematical programming (LP, MIP, decomposition methods) • Combinatorial optimization (assignment, scheduling, network flows) • Multi-objective optimization and control • Large-scale time-series forecasting (GenAI models, probabilistic forecasting, uncertainty quantification) • Causal inference (spatiotemporal causal modeling, offline policy evaluation) Preferred qualifications • Experience building optimization systems that run in production at scale • Being comfortable with ambiguity and fast iteration cycles • Publications in relevant venues Key job responsibilities Design and implement optimization and forecasting models for large-scale fulfillment problems, from order assignment to network flow control. Build research prototypes end-to-end: from problem formulation through scalable implementation to production validation. Analyse complex tradeoffs (cost, speed, capacity, accuracy) and translate findings into actionable recommendations for leadership and operations teams. Collaborate with engineers to bring science solutions into production systems serving millions of customer orders daily. A day in the life You formulate an optimization or forecasting problem on a whiteboard with teammates, then prototype it in Python with real data by the afternoon. You run experiments against production-scale datasets, iterate on the model, and present results to stakeholders who will use them to make network decisions next week. Some days you dive deep into solver performance; other days you're explaining a Pareto frontier to an operations leader. You collaborate with large engineering and product teams to bring your solutions into systems serving millions of customers. Alongside fast-turnaround prototypes, you own long-term research bets, the kind that reshape how Amazon's fulfillment network operates at scale. Your work goes live. About the team SCOT Fulfillment Optimization Science & Tech (FO SnT) is the applied research team behind Amazon's fulfillment decision-making systems. We decide how orders get assigned to warehouses, how capacity is allocated across the network, and how cost and speed tradeoffs are managed in real time, at global scale. Our models influence billions of euros in annual operational spend. They protect sites from overload during peak, reduce transportation costs and CO2 emissions, and ensure customers receive their packages when promised. Leadership relies on our science to make investment decisions worth hundreds of millions. We are practitioners of large-scale optimization: MIP formulations, decomposition methods, approximation algorithms, and parallelisation. We use machine learning where it sharpens our decisions, including forecasting, learned heuristics, and multi-armed bandits. We pick the right tool for the problem, not the fashionable one. You will work alongside Senior and Principal scientists, and collaborate with Amazon Scholars and academic partners who bring frontier research into our applied problems. We code our prototypes to be production-ready and collaborate with large engineering teams to ship systems, not papers. Above all, we have fun solving hard real-world problems at real-world speed, failing, learning, and shipping along the way.
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