As a Master's student in Machine Learning & Data Science at Université Paris Cité, I am driven by the pursuit of AI systems that can reason as well as predict. My experience ranges from designing and optimizing NLP pipelines at Safran Aircraft Engines to engineering end-to-end Retrieval-Augmented Generation (RAG) architectures that bridge information access and reasoning.
My current research, IMMUNE-Bench, explores how large language models can learn verification resilience—the ability to question, cross-check, and calibrate beliefs in adversarial information environments. I aim to contribute to the development of AI that thinks critically rather than confidently, combining rigorous technical design with a deep concern for epistemic integrity, interpretability, and AI ethics.
I am now seeking a visiting student researcher position to extend this work within a cutting-edge research group and prepare the ground for a PhD in applied AI research focused on robust, interpretable, and socially accountable intelligence.