Antoine Dedieu

Senior Research Scientist at Google DeepMind

San Francisco Bay Area United States
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

👤
Senior
🎓
Top School
Antoine Dedieu is a senior research scientist at DeepMind with a decade of experience building neuroscience-inspired, object-centric generative models for vision and scalable inference methods. He previously led research at Vicarious (acquired by Alphabet), where his work combining probabilistic graphical models and cognitive science delivered significant production wins—improving robot vision speed and accuracy by ~40% and powering a box-detection pipeline used over a million times. Trained at École Polytechnique and MIT (M.S. in Operations Research, perfect GPA), Antoine blends rigorous theoretical work in optimization and statistics with practical engineering, publishing multiple top-conference papers and shipping real-world systems. He has a track record of translating interpretable statistical estimators and novel optimization algorithms into deployable ML components, and often draws on neuroscience principles to make models generalize from limited data.
code10 years of coding experience
job8 years of employment as a software developer
bookMaster of Science (M.S.) Operations Research, Machine Learning - Optimization - Statistics. GPA 5.0/5.0, Master of Science (M.S.) Operations Research, Machine Learning - Optimization - Statistics. GPA 5.0/5.0 at Massachusetts Institute of Technology
bookMaster of Science (M.Sc.), Probability - Statistics - Optimization, Master of Science (M.Sc.), Probability - Statistics - Optimization at École Polytechnique
bookBaccalauréat, Major in Science, European Grade, Baccalauréat, Major in Science, European Grade at Lycée Emilie de Rodat - Toulouse
bookMathematics - Computer Science - Physics, Mathematics - Computer Science - Physics at Classe préparatoire Sainte Geneviève
languagesFrench, English, Spanish, Chinese
github-logo-circle

Github Skills (7)

belief-propagation10
bayesian-inference9
python8
jax7
compiler4
language-model2
reinforcement-learning2

Programming languages (3)

Jupyter NotebookMLIRPython

Github contributions (5)

github-logo-circle
google-deepmind/PGMax

Aug 2022 - Mar 2023

Loopy belief propagation for factor graphs on discrete variables in JAX
Contributions:3 releases, 22 commits, 25 pushes in 6 months
belief-propagationjaxbayesian-inferencepython
Contributions:43 pushes in 5 years
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