I am a Ph.D. student at the KAIST Graduate School of AI, co-advised by SungJu Hwang and SeongJoon Oh. Currently, I am based in Berlin working as an Applied Scientist Intern at Amazon.

My research interests lie in LLM post-training, with a focus on improving the reasoning and reliability of LLMs. Specifically, I investigate online post-training algorithms, including reinforcement learning and on-policy distillation, applied to AI safety and agentic tasks. My goal is to develop sample-efficient post-training methods and extend these frameworks to general, non-verifiable environments (e.g. Discovery).

Previously, I received my Bachelor’s degree in CS from KAIST. I have also gained industry experience as an intern at LG AI Language Lab, Naver, and NCSoft Speech AI Lab.