Scientific Consultant, Anthropic · Postdoctoral Associate, Virginia Tech
Exact physics. Checkable AI.
I am a theoretical physicist at Virginia Tech and a part-time Scientific Consultant at Anthropic. The big idea: physics already knows how to check itself — symmetries, anomalies, dualities, and consistency conditions. I turn those exact checks into feedback that AI agents can be tested and trained against.
Roles
Part-time consulting on research-level theoretical physics problems and evaluations for advanced reasoning, with emphasis on high-energy theory, supersymmetric gauge theories, dualities, and generalized symmetries.
Research in formal quantum field theory and string theory, focusing on generalized and non-invertible symmetries, SymTFTs, anomalies, brane engineering, and dualities.
Long-term research visit in the Department of Physics and Astronomy, collaborating on generalized symmetries, non-invertible symmetries, SymTFTs, and brane engineering.
Focus Areas
Generalized and non-invertible symmetries, SymTFTs, anomalies, dualities, and string-theoretic constructions of quantum field theories — with a focus on how categorical and topological structures organize quantum field theory data.
Building tools that check and improve how AI systems reason about fundamental physics — turning a model's claims into precise, auditable checks.
Asking whether concepts and organizing principles from theoretical physics can help formulate conceptual and mathematical frameworks for AI systems.
Selected Work
Contact and Profiles