François Rozet
PHD Student at F.R.S. - FNRS
Liège, Liège, Belgium
Summary
🤩
Rockstar🎓
Top SchoolFrançois Rozet is a PhD student in deep learning at the University of Liège, specializing in Bayesian inference for large-scale dynamical systems such as oceans and atmospheres. He blends theoretical interest in generative modeling and inverse problems with practical experience applying PyTorch-based methods and physics emulation. With seven years of experience across research, teaching, and industry internships (including a research stint at Polymathic AI), he contributes to university course codebases and hands-on projects, notably enhancing AI course material and student exercises. François has full‑stack and ML engineering experience in open-source course repositories, where he improved training pipelines, data augmentation, and even game-based teaching projects. Comfortable bridging pedagogy and research, he brings a pragmatic focus on reproducible, GPU-accelerated experimentation to tackle inference challenges at climate-relevant scales.
7 years of coding experience
Master of Science - MS Data Science and Engineering, Master of Science - MS Data Science and Engineering at University of Liège
French, English
Stackoverflow
584reputation
711kreached
19answers
1question
Github Skills (21)
pytorch10
python10
image-classification10
machine-learning10
game-development10
git-repository9
github-repos9
data-augmentation9
faster-rcnn8
data-structures8
mask-rcnn8
data-structure8
algorithms8
algorithm8
ssim6
Programming languages (9)
Github contributions (5)
glouppe/info8006-introduction-to-ai
Sep 2020 - Jan 2023
Lectures for INFO8006 Introduction to Artificial Intelligence, ULiège
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:38 commits, 33 PRs, 9 pushes in 2 years 3 months
Contributions summary:François contributed to the Pacman project by implementing features and fixing bugs across multiple projects. They added capsule functionality, unified score functions, and improved exercises. Their work involved modifying Python code, including changes to the game's core logic, and updating code exercises. The user's contributions show work in several project files.
deep-learningartificialmachine-learningulinatural-language-processing
glouppe/info8010-deep-learning
Feb 2022 - Mar 2022
Lectures for INFO8010 Deep Learning, ULiège
Role in this project:ML Engineer
ML EngineerContributions:5 reviews, 10 commits, 3 PRs in 13 days
Contributions summary:François primarily updated and modified code related to a deep learning course, specifically focusing on homework assignments. Their contributions involved addressing bugs in code, incorporating data normalization and augmentation techniques for image datasets, and optimizing model training procedures. The user also worked on classification tasks using multi-layer perceptrons, and explored the use of GPUs for faster computation. The majority of their work involves the use of PyTorch.
deep-learningulimachine-learningtensorflow
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.