I build infrastructure for AI agents — the systems that discover them, watch what they do, verify their output, and keep them governed. Mostly Go and TypeScript, usually with Postgres underneath.
Backend engineer at SuperAlign, working on enterprise discovery and governance for shadow AI: cross-platform scanner daemons, a realtime control plane for fleets of endpoints, and an extension SDK that ships telemetry into customer-owned Splunk and S3.
| Mindstate | Durable memory for AI agents over MCP — session handoffs, task-scoped recall, and memories that can be superseded rather than silently going stale. |
| miniqueue | A Postgres-backed job queue in Go. Lease semantics, at-least-once delivery, crash recovery — every tradeoff documented, tested against real Postgres. |
| kube-lite | Kubernetes' core ideas rebuilt from the ground up in Go: reconciler loop, scheduler, rollout controller, health probes, dead-node detection. |
| pgxray | Paste SQL, get an EXPLAIN ANALYZE plan tree and index suggestions grounded in your real schema. Read-only by construction. |
| bridgecord | Website chat that lives in Discord or Slack — one thread per visitor, with optional AI answers from your own site content. |
| markdown-to-video | Write a video in Markdown. Renders and exports to MP4 entirely in the browser. |
By taking them apart. A Redis server, a load balancer, Reed–Solomon erasure coding, a MITM proxy, React Query — rebuilt from scratch so I can explain why each piece exists, not just that it does.