About Me
The common thread throughout my work and interests has been trying to find and understand the underlying structures and invariants that might be lurking beneath surface perception and phenomena. For example, my belief that meaning lies in structure (and not the words, symbols, concepts themselves) has informed my approach to interpreting and securing AI systems, and before that, tracing adversaries through complex infrastructure.
I'm currently a mathematics PhD student at Imperial College London, under the supervision of Prof. Tom Coates and aligned with the London School of Geometry and Number Theory. I'm currently studying various aspects of algebraic and symplectic geometry, with a particular focus on quantum cohomology and computation of certain invariants. Beyond this, I'm interested in how cryptography, information theory, and philosophy can advance AI security and transparency.
Before starting my PhD, I was a senior AI security researcher at Microsoft on Dr. Andrew Paverd's team, where I worked on AI security vulnerabilities reported through our bug bounty program and LLM interpretability research. Before that, I was a Threat Hunter for advanced persistent threats across the foundational infrastructure running Azure, M365, and identity services. I also worked on infrastructure security and distributed systems software engineering at Amazon and AWS.
Please feel free to email me if you'd like to talk.
