Paris, France
AI Researcher · Data Scientist · Statistician
Recently graduated from ENSAE Paris and Institut Polytechnique de Paris with an MSc in Data Science & AI.
Research interests: Self-supervised Learning · LLM · RAG · ML · DS
News
Officially graduated from Institut Polytechnique de Paris with an MSc in Data Science.
Officially graduated from ENSAE Paris (IP Paris) with an MSc in Data Science & Statistics.
Paper accepted at IAAI-ALA 2025 is a part of ECAI 2025 — MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems. [link]
Joined Forvia as Data Science & AI Research Intern, working on hallucination detection on LLM and AI Agent applications [link]
Publications
IAAI Workshop @ ECAI 2025 · Bologna, Italy (CEUR-WS Vol-4136)
Proposes MetaRAG, a metamorphic testing framework to systematically detect hallucinations in Retrieval-Augmented Generation systems by evaluating consistency under controlled input transformations.
Experience
May – Nov 2025
Developed rapid prototypes for predictive maintenance and supply-chain decision-making, collaborating with embedded teams to deploy AI models within the digital cockpit stack.
Mar – Jul 2024
Built document intelligence pipelines combining large language models with compliance workflows, improving review throughput for regulated clients.
Jun – Sep 2023
Studied state-of-the-art LLMs and built a GPT-3.5/LLaMA-2 system to evaluate résumés against job descriptions, producing ranked candidate shortlists with explainable qualification decisions.
Education
2024 — 2025
Institut Polytechnique de Paris | IP Paris
Relevant courses: Deep learning, NLP, Advanced AI, Big Data, Reinforcement Learning.
2022 — 2025
ENSAE Paris
Relevant courses: Statistics, Machine Learning, Deep Learning, NLP, Bayesian Statistics, Econometrics, Optimal Transport, Macroeconomics, Microeconomics.
2019 — 2022
Institut de Technologie du Cambodge | ITC
Two years of intensive courses in Mathematics, Physics and Computer Science.
Projects
Research Implementation
Reproduced the convergence, regularization path, and debiasing results from Lénaïc Chizat (2024) using OTT-JAX and packaged the workflow in Google Colab for peers.
Delivered annotated notebooks and benchmarks validating annealed Sinkhorn behavior across datasets.
Python · JAX · OTT-JAX · Colab
VINCI · Jan–Apr 2025
Developing an essential retriever (LLM) that would be reboust enough to efficiently deal with generic use cases, but gnostic enough to be easily customized to deal with specific use cases. This would almost be like a package for information retrieval built for Python to service all LLM use cases that would want or need to use it
Built a flexible retriever module that can be easily integrated into RAG pipelines, improving retrieval relevance and reducing hallucinations across diverse applications.
Python · LangChain · HuggingFace · LLM
Data Science Sprint
Constructed composite indicators to score countries on education investment attractiveness, blending macro trends with education KPIs.
Produced a ranked list of countries with actionable insights for policymakers and investors, highlighting key drivers of education investment potential.
Python · PCA · EDA · Visualization
Collège de France · 2022–2023
Analyzed DEPP Premier Degré panel data to uncover determinants of mathematics performance gaps among French students.
Identified key socioeconomic and pedagogical factors to inform policy recommendations.
R · Regression · EDA · Policy Analysis