Zehao Jin (金泽昊) is an M.S. student in Computational Science and Engineering at the Georgia Institute of Technology, advised by Prof. Chao Zhang, and a 2025 B.S. graduate of Tsinghua University, where he worked with Prof. Yanan Sui. His research is on the alignment of large language models: mechanistic interpretability, safety and alignment, AI agents, and harness engineering — the neuroscience of LLMs. He has interned with the foundation-model teams at StepFun and Meituan LongCat.
Sections: News, Experience, Publications, Awards. Read his blog, or download his CV in English or Chinese.