Luca Cappelletti
Postdoctoral Researcher at Université de Fribourg - Universität Freiburg
Milan, Lombardy, Italy
Summary
🤩
Rockstar🎓
Top SchoolLuca Cappelletti is a software engineer and postdoctoral researcher with nine years of experience specializing in graph machine learning and biomedical knowledge graphs, currently contributing to the Digital Botanical Gardens Initiative for the Earth Metabolome Initiative. He bridges research and engineering, having implemented high-performance graph representation learning for precision medicine collaborations with Jackson Laboratory, Berkeley Lab, and Monarch Initiative. Luca has hands-on ML engineering experience in production-grade open-source projects—most notably enhancing Ray Tune (part of the widely used Ray project) with early stopping and Bayesian optimization integrations—and has extended functionality and stability in the Karate Club graph learning library. His background spans academic teaching, biomedical imaging pipelines, and building widely used web tools as a freelancer, reflecting both deep technical breadth and product-minded delivery. Based in Milan, he combines rigorous research training with practical software craftsmanship and a penchant for clean, well-tested contributions that improve reproducibility and scalability.
9 years of coding experience
7 years of employment as a software developer
University of MilanBachelor of Science - BS, Computer Engineering, Bachelor of Science - BS, Computer Engineering at Politecnico di Milano
English, Italian
Stackoverflow
2,515reputation
163kreached
67answers
16questions
python
top-5%
Github Skills (16)
scikit-learn10
hyperparameter-optimization10
machine-learning10
ray10
unsupervised-learning10
python10
scikit10
data-science9
word2vec9
networkx9
pytorch9
reinforcement-learning8
keras6
tensorflow6
numpy6
Programming languages (15)
Github contributions (5)
benedekrozemberczki/karateclub
May 2022 - Dec 2022
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
Role in this project:
ML Engineer
ML EngineerContributions:12 commits, 13 PRs, 13 pushes in 6 months
Contributions summary:Luca primarily contributed to the `karateclub` repository by addressing warnings, fixing typos, and resolving compatibility issues, suggesting a focus on maintaining code quality and stability. They exposed and documented parameters for existing machine learning models, demonstrating involvement in model optimization. The user also implemented new machine learning models, expanding the library's functionality.
node-embeddingpythonsklearngraph-clusteringpython-framework
ray-project/ray
May 2020 - May 2020
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Role in this project:ML Engineer
ML EngineerContributions:5 commits, 9 PRs, 29 comments in 6 days
Contributions summary:Luca's contributions center around enhancing the Ray Tune component, an AI compute engine for accelerating ML workloads. They added early stopping functionality, including `EarlyStopping` class and tests. Furthermore, they introduced new features related to integrating with Bayesian optimization and random search in Ray Tune, demonstrating an understanding of hyperparameter optimization techniques. The changes also included introducing patience functionality for early stopping, with associated tests and error handling.
pythonconsistsruntimetensorflowserving
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.