Hello! I’m Julian Baldwin, a 4th-year undergrad studying Computer Science at Northwestern. I’m currently doing research under V.S. Subrahmanian in Northwestern’s Security and AI Lab. This summer, I was at UChicago working on transformer interpretability under David Reber and Victor Veitch. Hoping to continue to build research skills and help make AI safe for humans.

I also love playing ultimate frisbee and indoor bouldering. I grew up in Seattle, WA; I don’t miss the gray skies, but I do miss hills.