Michael Scherbela
Research Scientist (ML) at Isomorphic Labs
Bern, Bern, Switzerland
Summary
👤
Senior🎓
Top SchoolMichael Scherbela is an ML research scientist with nine years of experience bridging physics, consulting, and computational science, currently training frontier AI models for drug discovery at Isomorphic Labs. He holds a PhD in Mathematics from the University of Vienna after pivoting from a technical physics background and a two-year stint at McKinsey focused on data and analytics. His work history spans computational chemistry, computer vision, automotive measurement techniques, and semiconductor test automation, giving him a rare mix of domain breadth and rigorous quantitative skill. Michael combines academic depth in ML and physics with product-minded research experience, and he has repeatedly moved between industry and academia to translate complex models into practical, high-impact applications. An Austrian-trained physicist now based in Bern, he quietly leverages consulting discipline to drive reproducible, scalable ML experiments in biotech.
9 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Mathematik, Doctor of Philosophy - PhD Mathematik at University of ViennaTechnische Universität Graz
Github Skills (22)
wave10
transfer-learning10
equation10
optimisation9
optimization9
python8
deep-learning8
automatic-differentiation8
machine-learning8
electron7
jit6
neural-network6
gpu6
composable6
autodiff6
Programming languages (2)
Github contributions (5)
mdsunivie/deeperwin
Sep 2021 - Aug 2022
DeepErwin is a python 3.8+ package that implements and optimizes JAX 2.x wave function models for numerical solutions to the multi-electron Schrödinger equation. DeepErwin supports weight-sharing when optimizing wave functions for multiple nuclear geometries and the usage of pre-trained neural network weights to accelerate optimization.
Contributions:2 releases, 1 review, 21 commits in 10 months
quantum-monte-carlopythonautomatic-differentiationsharingvariational-monte-carlo
MScherbela/kfac-jax
Jun 2022 - Oct 2024
Second Order Optimization and Curvature Estimation with K-FAC in JAX.
Contributions:2 PRs, 12 pushes in 2 years 4 months
second-orderoptimizationestimationcurvaturefac
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.