I'm a Research Fellow at Anthropic, working on neuropsychology for large language models. I'm currently interested in mechanisms of introspection.
Previously, I was a research scholar at MATS, working with Neel Nanda on mechanistic interpretability of LLM reasoning and chain-of-thought.
Before transitioning to safety and alignment research, I was a technology entrepreneur, having founded ventures in healthcare and education.
I also conducted research at Mila, where I specialized in neuroimaging.
I was the co-founder and chief technology officer of Heba Care, a digital care platform supporting individuals
with developmental differences and long-term conditions through tools, trackers, and expert guidance.
I co-founded Aiphabet, a New York-based non-profit dedicated to artificial intelligence education.
I graduated from Columbia University with a Bachelor of Science in computer science and applied mathematics.
I'm thankful to be advised by Ansaf Salleb-Aouissi and
Samuel K. Sia during my time at Columbia.
Outside of work, I'm a Fellow of the Royal Society of Arts (FRSA) and a
recipient of Aspen Institute's Rising Leaders Fellowship.
I'm a member of the Youth4Health network of the WHO Regional Office for Europe
and a mentor at Global AI Hub.
