Antoine Madrona is a data engineer with eight years of experience building production-ready ML and data solutions at the intersection of life sciences and finance, currently driving data initiatives at Isomorphic Labs in Lausanne. He has led end-to-end technical deliveries—from fine-tuning and benchmarking LLMs for enterprise use to architecting enterprise-grade GenAI infrastructure and data governance for biotech and financial clients. His background in life science engineering and hands-on R&D (including molecular biology internships and a federated learning master’s thesis on stroke imaging) gives him uncommon domain fluency for healthcare ML projects. An active open-source contributor, he has improved core time-series functionality in the widely used darts forecasting library, focusing on robustness for gaps and contiguous-slice computations. Colleagues rely on him for pragmatic design and rigorous testing practices that bridge research prototypes to scalable deployments. He’s particularly passionate about healthcare and time-series forecasting, combining domain knowledge with production engineering to turn complex biomedical data into actionable insights.
8 years of coding experience
4 years of employment as a software developer
Master's degree, Life Science Engineering, Minor in Data Science, Master's degree, Life Science Engineering, Minor in Data Science at Ecole polytechnique fédérale de Lausanne
Scientific French Baccalaureate, with Honours, Scientific French Baccalaureate, with Honours at Lycée International de Ferney Voltaire
A python library for user-friendly forecasting and anomaly detection on time series.
Role in this project:
Data Scientist
Contributions:367 reviews, 133 commits, 94 PRs in 3 months
Contributions summary:Antoine primarily contributed to bug fixes and improvements related to the "gaps" and "longest_contiguous_slice" functionalities within the `darts/timeseries.py` module, which is part of the core time series analysis and forecasting library. Their work included correcting bugs, adding tests, and addressing reviewer comments. The user also modified files related to the core functionalities of time series with the added functionality to work with component-specific lags. The user's work is centered around the core features of the library and improving the quality of the library.
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.