Victor Boussange
Scientific Collaborator
Zurich, Zurich, Switzerland
Summary
👤
Senior🎓
Top SchoolVictor Boussange is an interdisciplinary scientist and scientific collaborator with nine years of experience at the intersection of biomathematics, scientific computing, and machine learning, focused primarily on ecological and environmental applications. He holds a PhD from ETH Zurich and has held postdoctoral roles at ETH Zurich and WSL, now working at EPFL SCCS, where he develops hybrid methods that blend process-based models with machine learning to improve extrapolation and interpretability. A hands-on contributor to SciML (notably implementing and documenting multiple shooting in DiffEqFlux.jl), he brings production-grade numerical algorithm work—GPU-aware, stiff/non-stiff solver expertise—into research code. Comfortable moving between theory and applied software, he also has experience in energy modelling and lean automation, reflecting a practical engineering mindset alongside academic depth. Colleagues note his ability to turn complex ecological models into reusable, well-documented tools that generalize beyond ecology.
9 years of coding experience
3 years of employment as a software developer
Baccalauréat, Baccalauréat at Lycée Gustave EiffelDoctor of Philosophy - PhD Environmental Sciences, Doctor of Philosophy - PhD Environmental Sciences at ETH ZürichMaster of Science - MSc Engineering specializing in Energy and Environment, Master of Science - MSc Engineering specializing in Energy and Environment at INSA Lyon - Institut National des Sciences Appliquées de LyonUNSW Sydney
English, Spanish, French, German
Stackoverflow
1reputation
0reached
1answer
0questions
Github Skills (10)
differential-equations10
ensembles10
ode10
neural10
ordinary-differential-equations10
scientific-machine-learning10
julia10
optimization9
python6
pickle6
Programming languages (10)
Github contributions (5)
SciML/DiffEqFlux.jl
Aug 2021 - Aug 2021
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 8 commits, 1 PR in 2 days
Contributions summary:Victor's contributions center on the implementation and refinement of a multiple shooting algorithm within the `diffeqflux.jl` library. They have extended the functionality to support `EnsembleProblem` and improved the algorithm by resolving issues related to mutated arrays. The user also added documentation to enhance understanding and usage of the `multiple_shoot` function. Their work directly addresses the project's goal of providing tools for scientific machine learning.
scientific-machine-learningpartial-differential-equationsdifferentialodescientific-ml
SciML/HighDimPDE.jl
Apr 2021 - Dec 2022
A Julia package for Deep Backwards Stochastic Differential Equation (Deep BSDE) and Feynman-Kac methods to solve high-dimensional PDEs without the curse of dimensionality
Contributions:3 releases, 3 reviews, 307 commits in 1 year 8 months
automatic-differentiationscientific-machine-learningpartial-differential-equationscurseordinary-differential-equations
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.