I am the first Technical Director for Tufts AI Safety Student Association (TASSA), which was founded in Spring ‘25. We aim to address risks and harms emerging from the development and applications of advanced AI systems, from algorithmic bias to alignment. In my role, I help set directions/priorities for the organization and guide the development and facilitation of our technical fellowships.
I run our technical AI safety fellowships, which involve meeting weekly to discuss topics like transformer basics, reinforcement learning, model red teaming, and technical governance techniques. We ran our first iteration during the Fall '25 semester with a cohort of 12, and due to high demand, decided to expand the fellowship going forward.
My work is supported by funding and mentorship from Kairos's Pathfinder Fellowship, which has helped me build leadership skills in AI Safety and Ethics, and has given me the resources I need to make meaningful progress on these difficult problems through TASSA.