cv

Master 2, Machine Learning & Mathematics (MVA)

• Applied Mathematics & Machine Learning.
• Relevant coursework includes Probabilistic Graphical Models, (Geometric) Deep Learning, Time Series Analysis, Generative Modeling, Optimal Transport, LLMs, Random Matrix Theory, Bayesian ML, AGI Safety, Algorithms for protein science, Interactions.
• Partenered with APHP (Assistance Publique - Hôpitaux de Paris) to develop a LLM-powered tool for parsing and summarizing medical reports.

Master of Science (Cycle Ingénieur Polytechnicien)

• Applied Mathematics & Computer Science.
• Relevant coursework includes Statistics, Modeling, Random Processes, Stochastic Calculus, Statistical Physics, Optimization, Algorithms & Machine Learning.

Bachelor of Science (MPSI/MP*)

• Core curriculum in Mathematics, Physics, and Computer Science.

Exchange Student

• One incredible year with one incredible host family.

AI Scientist Intern

• Reasoning.

AI Research Scientist Intern

• Working on Knowledge Graph integration for Biological Foundation Models.

Quantitative Research Intern

Data Science Intern

• Analyzed charging point data and extracted valuable insights, with special focus on optimal charger dimensioning.
• Proposed new real-time charging point KPIs for Operations Dashboard.

Officer Cadet

• Assistant to Head of Commando Division.
• Military training & personal development.

Horseshoe Prior

• Theoretical study and NumPyro implementation of the Horseshoe Prior, a popular Bayesian variable selection method.

Minority Game

• Simulation and empirical study of the Minority Game, a repeated binary prediction game which exhibits emergent behaviors revolving around the idea of self-organization.

LLM-Powered Medical Report Summarization

• Partenered with APHP (Assistance Publique - Hôpitaux de Paris) to develop a LLM-powered tool for parsing and summarizing medical reports of scanners for both doctors and patients.

Diffusion Schrödinger Bridge

• Theoretical study of the Schrödinger Bridge problem & PyTorch implementation of the Diffusion Schrödinger Bridge algorithm to study convergence properties in the Gaussian case.

Equivariant Diffusion for Molecule Generation in 3D

• Demonstration of the benefits of incorporating E(3)-equivariance in Graph Neural Networks through toy model experiments on the QM9 drugs dataset.

Score-Based Generative Modeling

• Theoretical study of Score-Based Generative Modeling & PyTorch implementation to compare Langevin, SDE and ODE sampling methods. Also explored controlled generation techniques, including conditional generation and inpainting.

High-Frequency Volatility Estimation

• Implementation of non-naive volatility estimators for high frequency financial data by accounting for microstructure noise & Modeling high-frequency price dynamics using Hawkes processes. Theory tested on EUR/USD tick data.

Signature Trading

• Theoretical study of the signature object and its application to portfolio optimization. Implementation of a signature-based trading strategy on synthetic data to reproduce and extend results from the literature.

Knowledge Graph of Mathematics

• Built a RDF graph of mathematics on Neo4j using data queried from Wikidata and scraped from Wikipedia. Analyzed and visualized the graph using Gephi.

Solving simple PDEs using MCMC

• Implemented a probabilistic approach relying on Markov Chains Monte Carlo to solve simple partial differential equations with Dirichlet conditions.

Algorithmic Collusion

• Developed dynamic pricing algorithms which utilize reinforcement learning to determine the optimal retail price on a market with other participants also dynamically updating their prices. Trained different classes of RL pricing agents and observed their collusive behavior in various simulated economic environments, thus demonstrating the robustness of algorithmic collusion.