ai infrastructure · harnesses · agents · evals · graphs · inference engineering
i build ai systems that reason — not just retrieve. the work lives in the seams: harnesses that hold models accountable, agents with bounded agency, evals that catch failure modes before they ship, inference engineering that makes it run where it matters.
security roots. editorial eye. accuracy > speed.
| languages |
|
| ai / ml |
|
| infra / ops |
|
| frontend / 3d |
|
| project | what it does | stack |
|---|---|---|
| razorpay-agent | conversational ai for payment flows, refunds, reconciliation | Python Razorpay API |
| gREV | rl sandbox that trains agents to fix code during ci/cd | Python Docker OpenEnv |
| NetSieve | real-time nids with sha-256 chained forensic logger | C Bare-metal |
| LastLook | structured workspace for fellowship & hackathon applications | TypeScript AI |
