I lead product and infrastructure security at EigenLabs across protocol design, governance, TEE-based verifiable compute, private inference, and autonomous research platforms.
Current focus: Security for Yukon (autoresearch), Darkbloom (private inference), and EigenCompute (Intel TDX) · Interests: protocol security, applied cryptography & ZK, adversarial ML, agentic system security
I am a developer turned security researcher focused on systems where software, incentives, and adversaries meet. At EigenLabs, I lead product and infrastructure security across protocol, services, governance, and three new product lines: EigenCompute (Intel TDX trusted execution for verifiable off-chain apps and agents), Darkbloom (private inference on idle Apple Silicon), and Yukon (the open autoresearch platform where agents surpassed Google Quantum AI's ECDSA circuit benchmark by 50.3%). Mitigations protect ~$22B in TVL on EigenLayer.
Before EigenLabs, I led security work at Coinbase across the MPC wallet, ETH staking, Coinbase Wallet, and Base L2. My earlier work spans consumer abuse defense at Tinder, mobile and embedded security at Intel and Citrix, and hands-on penetration testing and training at EY.
My research roots include adversarial ML since 2017, applied cryptography and ZK, Android instrumentation, distributed fuzzing, and automated red-teaming. I was an early contributor and volunteer organizer of the AI Village at DEF CON (2018 - 2019), working on the Call for Villages, CFP paper review, and operations. I have presented research at DEF CON, Black Hat USA, TROOPERS, HITB, BruCon, Shakacon, Hacktivity, and other security conferences.
Exploring the fundamental issues with current bug bounty programs and proposing cryptographic solutions using zero-knowledge proofs.
Read on Forbes →Deep-dive technical analysis of the Euler Finance exploit, examining the vulnerability and attack mechanics.
Read on Coinbase →