About me
I'm the AI Lead at Corridor, where we build the security layer for AI coding agents — guardrails that reach the agent while it's still planning, automated pull request review, and an observability layer over everything it writes. Most of my time goes to agent security evaluation: red-teaming coding agents and building the benchmarks that show where their blind spots are.
I got here from both sides of the problem. I was a founding engineer at Vooma, a machine learning engineer at PayJoy, and co-founder / CTO of Gradia Health (YC W21); before that, a research engineer at Stanford CRFM, working on HELM and publishing on benchmark construction and safety evaluation. Based in the Bay Area — and we're hiring at Corridor.
Recent work
The security layer for AI coding agents
Corridor reaches coding agents like Claude Code, Cursor, and Copilot through an MCP server and agent hooks — reviewing an agent's plan before any code is written, then reviewing the pull request it opens. I lead the AI work behind it.
AgentBreaker
A blind spot detector for your coding agents — a talk with Aditi Narasimhan on the Creator Stage. Coding agents fail in ways traditional application security tooling never looks for, so we went looking for them systematically.
AutoBencher
Benchmark construction as an optimization problem: declare what you want — difficulty, salience, novelty — and let a language model search for datasets that satisfy it. The result elicits 22% more model errors than the benchmarks it replaces.
HELM Safety
Safety evaluations usually run behind closed doors, which leaves the public unable to interpret them. HELM Safety is the public alternative: standardized benchmarks across six risk categories, run over two dozen leading models.
Some of my interests include:
Get in touch
Always up for a conversation about AI safety, agent security, or evals — and we're hiring at Corridor.