Skander Moalla
Research Scientist Intern at EPFL IC
Lausanne, Vaud, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolSkander Moalla is a final-year PhD candidate in reinforcement learning and LLM post-training at EPFL with seven years of research and engineering experience across academia and industry, currently interning at Meta FAIR. He specializes in scaling RL for large language models, developing off-policy and offline fine-tuning algorithms (e.g., Quantile Reward Policy Optimization) and exposing links between plasticity, trust regions, and off-policy collapse. Skander has co-led post-training of a fully open-source 70B LLM (Apertus 70B), contributed production-grade JAX code at DeepMind, and built scalable pipelines and sandboxes for reproducible ML experiments. Comfortable shipping infrastructure and research code from scratch, he combines rigorous theoretical work with hands-on systems development and a track record of award-winning reproducibility studies. Open to full-time roles in Zurich, Paris, or London for Fall 2026, he brings a rare blend of RL theory, LLM post-training expertise, and practical engineering at scale.
7 years of coding experience
1 year of employment as a software developer
Master of Science - MSc, Advanced Computer Science, Master of Science - MSc, Advanced Computer Science at University of OxfordExchange program - Fall semester, Mathematics and Computer Science, Exchange program - Fall semester, Mathematics and Computer Science at University of TorontoBaccalauréat, Mathématiques, Baccalauréat, Mathématiques at Lycée Pilote Bourguiba de TunisBachelor of Science - BS, Mathematics and Computer Science, Bachelor of Science - BS, Mathematics and Computer Science at École PolytechniqueDoctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at EPFLInternational Honors Program (IHP) - Summer quarter, Technology and Innovation Intensive studies, International Honors Program (IHP) - Summer quarter, Technology and Innovation Intensive studies at Stanford University
Arabic, French, English, German
Github Skills (100)
multi-agent-reinforcement-learning10
python10
gymnasium10
distributed-computing10
deep-learning10
gpu10
multiagent-systems10
robotics10
modular10
api10
ai10
decision-making10
hyperparameter-tuning10
deep-reinforcement-learning10
nlp10
Programming languages (8)
Github contributions (5)
orausch/graphrnn
Mar 2022 - Apr 2022
Contributions:65 commits in 18 days
skandermoalla/Top5
Nov 2018 - Mar 2019
Basketball team Manager game simulation
Contributions:8 PRs, 99 pushes, 13 branches in 4 months
gameteam-managermanager-gamesimulationsimulation-game
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.