I'm an Anthropic Safety Fellow and fourth-year PhD student at MIT CSAIL, advised by Dylan Hadfield-Menell.

I do pragmatic AI safety research with the hope of reducing catastrophic risks from powerful AI systems.

Previously, I obtained my bachelor's degree at Johns Hopkins, where I worked with Professor Rene Vidal on the theory of deep learning. During undergrad, I also worked with Dyno Therapeutics on ML-guided protein design.

Outside of work, I enjoy playing piano, backpacking, salsa dancing, and philosophy.

Reach out at stew@csail.mit.edu if you'd like to talk! Leave anonymous feedback for me here.

Google Scholar Resume Goodreads