Broadly interested in AI security & safety (control research), formal verification, AI for science, LLMs, and self-organizing systems.

I'm currently:

• Incubating Enclave Intelligence and Xchg Labs, working across AI transformation, applied AI, AI security, and vuln research/reverse engineering.
• A visiting researcher at the AI Innovation Institute (AI3) at Stony Brook University, working on formal verification & AI safety.