Mirco Milletari
Principal Applied Scientist at Microsoft
Bellevue, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolMirco Milletari is a Principal Applied Scientist with nine years of industry experience who transitioned from a PhD in theoretical condensed matter physics to driving machine learning and recommender system work at Microsoft. He combines deep quantitative expertise and creative, cross-disciplinary problem solving—applying tools from physics, mathematics and biology—to build and validate robust ML models in production. Mirco has worked across the U.K., Germany, Singapore and the United States, bringing strong cross-cultural communication and a track record of conference presentations. His open-source work includes rigorous unit testing for RBM components in a prominent recommenders repo, reflecting attention to model integrity and reproducible engineering. Outside work he channels curiosity into sports, photography and gaming, a blend that informs both analytical rigor and creative approaches to complex system design.
9 years of coding experience
9 years of employment as a software developer
Master of Science (MS) Theoretical and Mathematical Physics, Master of Science (MS) Theoretical and Mathematical Physics at University Roma TreDoctor of Philosophy (PhD) Theoretical condensed matter physics, Doctor of Philosophy (PhD) Theoretical condensed matter physics at Max Planck Institute for Solid state research and University of Leipzig
Italian, English, German, Spanish, mathematics
Github Skills (11)
machine-learning10
recommendation-system10
pytest10
python10
data-science10
testing10
jupyter-notebook8
data-structures8
scikit8
scikit-learn8
data-structure8
Programming languages (3)
Github contributions (5)
recommenders-team/recommenders
Dec 2018 - Feb 2019
Best Practices on Recommendation Systems
Role in this project:
ML Engineer / Data Scientist
ML Engineer / Data ScientistContributions:108 commits, 3 PRs, 29 pushes in 1 month
Contributions summary:Mirco implemented and tested unit tests for an RBM (Restricted Boltzmann Machine) splitter, including creating synthetic datasets and validating the matrix dimensions and split ratios. This involved writing test code in Python, integrating with the Pytest framework, and verifying core functionality related to the RBM algorithm, specifically within the context of a recommendation system. The user demonstrated a clear understanding of model testing and ensuring data integrity.
recommendation-systemspythonjupyter-notebookoperationalizationmicrosoft
WessZumino/meanfield-theory-of-activation-functions
May 2018 - Jun 2019
Contributions:57 commits, 48 pushes, 3 branches in 1 year
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.