Frontier-model deployment · AI governance & observability · agentic engineering · regulated fintech
I get frontier models into production in places where the regulatory and security bar is high. Anyone can demo an agent. The hard part is the substrate underneath: review gates, observability, permission boundaries, and a hard rule that AI never touches the system of record.
- Agentic engineering at Antech. Claude Code and Copilot workflows that built a support platform end to end and automated unit testing — a 4.2x velocity increase on measured delivery.
- A decade in regulated fintech and digital assets before that: CCSS Level 3 custody, wrapped tokens at $100M+ TVL, and recovery tooling that scanned vaults across 20+ EVM networks to bring back $4M+ in stranded assets.
~20 years of engineering, principal/staff level. I reach for frontier models plus retrieval before fine-tuning, almost every time.
I don't train models and I'm not a prompt engineer. I'm the person you bring in when the demo worked and now it has to survive compliance.
AI/LLM engineering: Claude, GPT, agentic workflows, RAG, MCP, AI governance, LLM observability, prompt/skill marketplaces, Claude Code, GitHub Copilot Languages & platforms: C#/.NET, Python, TypeScript/React, SQL Infrastructure: Azure, AWS, OpenTelemetry Domain: regulated fintech, digital asset custody, commercial lending, compliance-grade software delivery