I am a Research Scientist at Snowflake AI Research, where I work on LLM reasoning and agentic frameworks, with a particular focus on how reinforcement learning (RL) contributes to these emerging paradigms.

I received my Ph.D. in Computer Science from UC San Diego, where I was fortunate to be advised by Prof. Yian Ma, and closely collaborated with Prof. Tara Javidi, Prof. Sean Gao. During my PhD, I primarily work on RL, foundation Models (LLMs, Diffusion Models) and Bayesian inference, with the aim to address the fundamental challenges in sequential decision-making under uncertainty. The goal of my research is to design provably efficient and practical algorithms with performance guarantee, achieving both statistical and computational benefits. Besides, I have gained hands-on experience with fine-tuning LLMs and reward models, designing CoT prompting and reasoning frameworks, LLM decoding, and training R1-style reasoning LLMs using RL (e.g. PPO, GRPO).

Previously, I interned at IBM research, Amazon and Honda Research Institute, working on LLM for personlization, RL for ranking and recommendation systems, and robotics.