Benjamin Clavié

Member Of Technical Staff at Mixedbread

Mitaka, Japan
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Benjamin Clavié is an AI researcher and NLP engineer with a decade of hands-on experience designing and shipping language-driven products and R&D initiatives across startups, consultancies, and academia. Based in Musashino, Japan, he has led machine learning teams and built retrieval-augmented LLM applications and production NLP systems for clients and legal-tech platforms, blending research rigor from an MScR in Artificial Intelligence with practical delivery. His background spans roles from Lead Data Scientist and Machine Learning Lead to research-and-teaching at the University of Edinburgh, giving him a strong bridge between experimental methods and production engineering. Colleagues value his ability to translate cutting-edge LLM techniques into consultative, client-focused solutions—often surfacing pragmatic trade-offs that aren’t obvious from experimental papers alone.
code10 years of coding experience
job6 years of employment as a software developer
bookMaster of Science by Research (MScR), Artificial Intelligence, Master of Science by Research (MScR), Artificial Intelligence at The University of Edinburgh
bookDoctor of Philosophy, Informatics (Artificial Intelligence), Doctor of Philosophy, Informatics (Artificial Intelligence) at The Graduate University for Advanced Studies, SOKENDAI
languagesFrench, English
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (85)

language-model10
bug-reporting10
nbdev10
encoder10
nlp10
retrieval10
python-modules10
documentation-generator10
natural-language-processing10
pypi10
llm10
bert10
chatgpt9
multimodal9
recommender-system9

Programming languages (8)

TypeScriptMDXC++RustCJupyter NotebookRubyPython

Github contributions (5)

github-logo-circle
AnswerDotAI/RAGatouille

Dec 2023 - May 2025

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Contributions:13 releases, 36 reviews, 93 PRs in 1 year 4 months
bclavie/edubert

Dec 2019 - Apr 2020

Contributions:10 commits, 11 pushes, 1 branch in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial