Machine learning scientist and computational physicist with strong programming expertise in Python and experience working in international, multidisciplinary environments. Currently applying ML to model calibration and anomaly detection at ITER Organization, with a solid foundation in scientific research, algorithm development, and open-source software. Passionate about solving complex technical challenges in nuclear fusion and R&D settings.
Please do not hesitate to reach out with any questions or feedback you may have about my research or my personal projects.
PhD. in Computational Physics, 2021
University of Montpellier
MSc. in Computational Physics, 2018
University of Montpellier
BSc. in Theoretical Physics, 2016
University of Montpellier
Publications, code releases, recent activity
Contributed to ITER, the world’s largest international scientific collaboration, aiming to demonstrate the feasibility of large-scale clean energy from nuclear fusion. Designed a machine-learning-based calibration strategy for ANSYS finite-element models using Bayesian optimization and Gaussian processes. Developed anomaly detection algorithms for predictive maintenance, enabling intershot and real-time monitoring. Contributed to the Tokamak Systems Monitor software, including version control and data handling (Git, DVC). Administered the team’s multi-GPU compute server. Presented results at international conferences (SOFT, SOFE) and workshops (Fusion for Energy AI Workshop). Explored LLMs for automated tokamak operation reporting. Co-supervised interns and supported external contributors.
Machine learning
| Artificial intelligence
| Python
| Nuclear fusion
| FEA
| Ansys
| Mechanical engineering
Research on the emergence of local order in disordered materials such as glasses and supercooled liquids using molecular dynamics simulations, unsupervised machine learning (clustering, dimensionality reduction, autoencoders), and information theory. Developed a fully documented open-source Python package (partycls) for machine-learning-based structural analysis, with CI/CD integration. Ran large-scale simulations on CPU and GPU clusters. Presented work at international conferences and workshops. Delivered 200+ hours of undergraduate teaching in physics and programming.
Computational physics
| Machine learning
| HPC
| Python
| C++
| Fortran
| Teaching
Performed quantum simulations to study the electronic and vibrational properties of complex 2D materials. Hands-on experience with large-scale simulations on HPC clusters. Attended international summer schools on parallel computing (MPI, OpenMP, CUDA) and quantum physics for materials science.
– Financed by the RQMP international internship grant program.
Computational physics
| Quantum physics
| Parallel computing
| Python
Performed Raman scattering and reflectometry experiments on graphene samples using complex experimental setups. Contributed to the development of a LabVIEW application for automating measurements and used Python for data analysis.
Experimental physics
| Python
| LabVIEW
Fabricated complex heterostructures through mechanical exfoliation and stacking of 2D materials. Characterized materials using Raman spectroscopy and white-light reflectometry. Authored a microscope user manual for training graduate students in optical characterization.
Experimental physics
| Python
Developed Python models and ran simulations to study how opinions propagate on small-world networks. Explored consensus dynamics and decision-making processes by systematically varying model parameters and assumptions. Conducted extensive data analysis to evaluate behavioral patterns and outcomes across different scenarios.
Computational physics
| Python
| Network theory
Research and personal programming projects
Online courses