Researcher · Open-Source Contributor · Engineer

Researcher interested in multi-agent systems and AI security. IEEE-published across multiple papers. Active open-source contributor. Building open security primitives for AI agent accountability.

Multiple IEEE-published papers spanning AI systems, NLP, and software engineering. Current research focus: multi-agent systems security, specifically the accountability gap in autonomous agent runtimes: what agents do, in what order, and whether the record can be trusted. Working at the intersection of cryptographic audit infrastructure and AI agent behavior.

Active contributor spanning Lexical, tldraw, and TipTap : focused on correctness bugs and interaction precision that affect real end users at scale.

Building open security primitives for AI agent accountability. Core work: tamper-evident audit infrastructure for multi-agent systems using cryptographic hash chains, Ed25519 signatures, Merkle commitments, and formal evidence classification, so that when an autonomous agent acts, there is a verifiable record that no one changed. Complete systems with documented threat models, not demos.

• Multi-agent systems security and agent accountability infrastructure
• Cryptographic audit primitives for autonomous agent runtimes
• AI agent behavior analysis and tool-use auditing
• Production open-source contribution

Open to research collaborations in multi-agent systems and AI security. If you're working where correctness and depth matter, let's talk.