Summary
Rui Yuan is an AI Research Scientist based in Paris with 10 years of experience bridging applied mathematics and cutting-edge LLM research. He holds a PhD in Applied Mathematics from a Meta AI–Télécom Paris CIFRE program and has driven generative AI, in-context learning, and RLHF work at Stellantis before focusing on reinforcement-learning fine-tuning for LLMs at Lexsi Labs. His background spans reinforcement learning, optimization, and deep learning, and he brings practical large-scale engineering experience from industry internships involving Hadoop, Spark, and production-ready predictive models. Rui combines rigorous theoretical training with hands-on experimentation in RLFT and in-context adaptation, often translating optimization insights into scalable model fine-tuning strategies. Notably, his early research on stochastic optimization and parallel primal-dual methods was recognized at JDSE2018, reflecting a long-standing thread of marrying algorithmic theory with applied systems.
10 years of coding experience
3 years of employment as a software developer
Master of Science (MSc) Mathematics Computer Vision and Machine Learning, Master of Science (MSc) Mathematics Computer Vision and Machine Learning at ENS Paris-Saclay
High School, High School at The Affiliated High School of South China Normal University
Master of Science - MS Data Science, Master of Science - MS Data Science at École Polytechnique
MPSI-MP** Mathematics Physics Chemistry Computer Science, MPSI-MP** Mathematics Physics Chemistry Computer Science at Lycée Janson-de-Sailly
English, French, Chinese, Chinese