Kaley Brauer

AI Safety Researcher | Computational Astrophysicist

I research interpretability and alignment of large language models as a MATS AI Safety Fellow at OpenAI. I am also an NSF Astrophysics Postdoctoral Fellow at Harvard.

Previously, I received my Physics Ph.D. from MIT and Physics Sc.B. from Brown.

When I am not doing research, I enjoy dancing, biking, and science writing. My astronomy children's book will be out in a few months!

CV: view here
EMAIL: kaley.brauer@cfa.harvard.edu

RECENT NEWS

	Harvard News: Analog Astronaut Kaley Brauer Explores the Human Side of a Mars Mission Apr 1, 2026: Article describing an analog astronaut mission I worked on as Crew Scientist. My crew and I studied how humans might someday live and do research on other planets.
	RCSA Fellows Initiative Selects 2025 Cohort Apr 11, 2025: Article describing the 2025 cohort of Research Corporation for Science Advancement's Fellowship Program. The fellowship includes professional development workshops and community building.

See all news →

Hello from the Magellan Telescopes in Chile