I am a Computational R&D Engineer at Michelin, working on industrial finite element frameworks and machine learning-based simulation tools. I hold a PhD from the Conservatoire National des Arts et Métiers (CNAM) in Paris, where my research focused on Machine Learning strategies for accelerating numerical simulations of fluid-structure interaction.

My work lies at the intersection of scientific computing, machine learning, and computational mechanics. I develop data-driven reduced order models, multiphysics coupling strategies, and ML-enhanced numerical methods to accelerate complex simulations.

Research Interests

• Reduced Order Modeling: Manifold learning, Dynamical systems, DMD.
• Fluid-Structure Interaction: Partitioned coupling schemes, black-box coupling, convergence acceleration.
• Scientific Machine Learning: Hybrid physics-ML methods, system identification, Data-Driven Computational Mechanics (DDCM).
• Computational Mechanics: Finite element method, multiphysics simulations, nonlinear solvers.

Background

I obtained my engineering degree in Mechanical Engineering from ENSAM (École Nationale Supérieure d’Arts et Métiers) in Paris (Silver Medal - Rank: 83/1180). I then pursued a PhD at CNAM in collaboration with Michelin and Altair, supervised by Pr. I. Mortazavi, Pr. F. De Vuyst, T. Dairay, and J-P. Berro Ramirez.

I am also an active contributor to open-source scientific software. See Software.

I’m having fun being the sole maintainer (and probably the user ) of ROM_AM, a non-intrusive reduced order modeling package I started developing during my PhD.