Principal Engineer specializing in distributed systems, cryptography, and blockchain infrastructure.

Track record: • Open source maintainer — 35M+ downloads across Rust infrastructure libraries (rust-s3, goauth, aws-creds) • High-scale systems — bot detection at 5B requests/day (hCaptcha) • Protocol design — post-quantum secure channels, mix network packet formats achieving 10x throughput • Blockchain infrastructure — 30+ chains in HA setup, first provider in Bloomberg ecosystem • Smart contracts — epoch-based tokenomics with stake saturation and sybil resistance (CosmWasm)

Currently building AI agent tooling: • Agneto — autonomous development system that orchestrates 9 specialized AI agents (planning, coding, reviewing, cleanup) with human oversight at decision points. All work happens in isolated git worktrees, so main branch is never touched. • Superego — metacognitive advisor for Claude Code. Hooks into AI coding sessions at key checkpoints, evaluates approach against project conventions, and provides feedback the AI acts on before finishing. Creates feedback loops where the AI course-corrects during work, not after.

The thesis: AI agents need structure, not freedom. Sandboxed execution, explicit checkpoints, audit trails, human-in-the-loop at decisions that matter. The same principles that make distributed systems reliable make AI systems trustworthy.

Background in behavioural psychology (PhD) — research design, statistics, and understanding why systems fail at the human layer. That training turns out to be useful when designing systems where humans and AI collaborate.

Writing Rust since 2016.

Top posts