Federico Vaggi
Machine Learning Lead Senior Staff Scientist at X, the moonshot factory
Seattle, Washington, United States
Summary
👤
Senior🎓
Top SchoolFederico Vaggi is a Machine Learning Lead and Senior Staff Scientist with 13 years of experience bridging physics, computational biology, and production ML at organizations from Amazon to Google X. He specializes in causal inference, probabilistic modeling, and mathematical approaches to complex systems, favoring the simplest effective methods rather than tool-driven solutions. At Google X he works on early moonshot problems involving large language models, optimization, and computational modeling, and at Amazon he led applied science efforts in Bayesian counterfactual forecasting and FBA fees optimization. Federico contributes to open source QA and scientific computing—improving debugability and test automation for projects like diffrax (JAX differential equation solvers) and scikit-learn. Trained as a physicist and molecular biologist (PhD), he combines rigorous theoretical modeling with pragmatic engineering, often translating differential-equation and network-based insights into robust, testable ML systems.
13 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (PhD), Molecular Biology, Doctor of Philosophy (PhD), Molecular Biology at University of MilanBachelor of Science (B.Sc.), Physics, Bachelor of Science (B.Sc.), Physics at Imperial College, LondonSingapore American SchoolMaster of Science (MS), Bioinformatics, Master of Science (MS), Bioinformatics at University of Milano, Bicocca
English, Italian
Github Skills (14)
scikit-learn10
scikit10
machine-learning10
error-handling10
differential-equations10
jax10
pytest10
python10
test-automation10
testing10
data-science9
deep-learning8
neural-network8
data-analysis8
Programming languages (8)
Github contributions (5)
scikit-learn/scikit-learn
Feb 2013 - Jul 2013
scikit-learn: machine learning in Python
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:7 commits, 13 comments in 5 months
Contributions summary:Federico primarily focused on adding and improving testing infrastructure for the scikit-learn library. They implemented new tests for pickling estimators and transformers to ensure model persistence and correctness. Furthermore, the user added a test suite to compare different classifiers using partial fit methods, demonstrating a strong understanding of testing and model validation within a machine learning context. They also refactored the code to improve performance and maintainability by changing the way objects were serialized.
data-analysispythonstatisticsdata-sciencelearn-machine-learning
patrick-kidger/diffrax
Feb 2022 - Feb 2022
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Role in this project:Back-end Developer & QA Engineer
Back-end Developer & QA EngineerContributions:1 review, 5 commits, 1 PR in 6 days
Contributions summary:Federico primarily focused on improving error handling and debugging capabilities within the `diffrax` library. They made multiple commits adding more descriptive error messages, including the values and types of variables, to aid in debugging. Additionally, the user integrated and configured pytest for the project. This focused on quality assurance and test automation.
equationdeep-learningdynamical-systemsgpusolvers
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.