About
I grew up curious about how things fit together — tools, patterns, and encoded rules. That instinct focused into computation, geometry, and structure.
I build and study systems where ideas become structure and structure becomes clarity. This site is a working archive — a place to collect and refine the systems I study and build over time.
My work sits at the intersection of mathematics, machine learning, and reproducible infrastructure. I approach every problem as a systems question: what are the inputs, constraints, and feedback loops? Whether designing ML pipelines or building research tooling, the underlying method is the same — observe carefully, model rigorously, iterate.
Research interests
Mathematical structure, interpretable machine learning, computational number theory, discrete mathematics, and the design of tools that make complex inquiry more traceable and reproducible. ProofX is the primary vehicle for this work.