Max Hartman

I'm a Research Engineer at Corridor, working on Applied Research and Evals for Coding Agent Security. Previously, I was an MS student in the UIUC ECE department, advised by Prof. Lav R. Varshney and Prof. Minh N. Do. My research centers on AI safety, efficiency, and privacy in large language and vision-language models, with additional interests in interpretability, reasoning, and post-training. I enjoy working on theoretically-grounded, experimental research, using tools from information and control theory to explain model behavior.