Building for an agent-first world.
With a decade of hands-on engineering—from global enterprises to AI infrastructure—I now focus on AI agents and the systems behind them.
Curious by default. Grounded in engineering. Interested in what's next—and what it takes to make it work.
- AI Agents: Making intelligent systems useful in practice.
- Developer Infrastructure: Better foundations for building with AI.
- Open Source: Contributing to the tools behind the ecosystem.
I'm also interested in fintech—and the underlying infrastructure that moves value.
| Project | Contribution |
|---|---|
| Microsoft Agent Lightning #573 | Preserve requests without valid prompt token IDs |
| NVIDIA SkillEvaluator #84 | Prevent false-positive runtime errors in agent transcripts |
| NVIDIA SkillEvaluator #106 | Scope Gitleaks to the checked-out Git history |
| Burn #5494 | Preserve extensionless Burnpack paths |
| Technocore #135 | Prevent HEAD requests from executing write routes |
| Project | Contribution |
|---|---|
| OpenAI Agents SDK #4739 | Preserve Pydantic Field constraints on variadic tool parameters |
| OpenAI Agents SDK #4748 | Release unused SQLAlchemy table-initialization locks |
| Claude Agent SDK #1237 | Surface subagent import I/O failures instead of hiding them |
| Claude Agent SDK #1238 | Deduplicate subagent IDs across session storage paths |
| NVIDIA NeMo Evaluator #1153 | Include the full request body in adapter cache keys |
| Stripe AI #509 | Stop consuming abandoned token-meter streams |
Status checked on August 30, 2026. Browse all of my pull requests.
Python, Go, Rust, and TypeScript are the tools I reach for most. The interesting part is making the pieces work together.