mentorship

Initiative supporting alignment research and community-building across the Cambridge–Boston area. I serve as a research manager for participating fellows.

Undergraduate and graduate group at Harvard focused on technical AI safety. I lead technical development and mentor students on research projects in alignment, interpretability, and evaluation.

Student-led alignment community at MIT. I teach the ARENA program, the AI Safety Education program developed by the London Initiative for Safe AI, and help shaping its curricula to the MIT community.

Remote research program pairing junior researchers with mentors on alignment and safety projects. I mentor SPAR fellows on technical research directions.