Engineer and engineering manager. 17 years building payments, trading, and e-commerce systems and leading distributed teams. Lately I work across AI-assisted engineering and AI agent tooling. Based in Vancouver, BC.
- purpl-brain: decision memory and a pre-action guardrail for codebases edited by multiple independent AI coding agents. An agent calls
analyze_impactover MCP to see which prior decisions a change would break before it writes code. Neo4j decision graph plus Qdrant semantic search, so contradictions that share no wording are still caught. Write-up. - career-ops interview modes: plan, practice, and debrief modes plus the session-transcript producer, merged into santifer's career-ops. Built to its never-fabricate rule; other contributors' features now build on the transcript format.
- Repo-context-aware AI code review: RAG over repository context (n8n, Qdrant, LLMs) that generates project-specific feedback on GitHub pull requests.
Java, Node/TypeScript, Next.js · distributed systems, microservices, event-driven · PostgreSQL, MySQL, SQL Server · AWS (EC2, S3, Lambda, SQS), Docker, CI/CD · RAG, MCP servers, agent memory & guardrails · Neo4j, Qdrant, Claude Code, Ollama
17 years building payments and back-office systems at D. E. Shaw, Arcesium, and Elastic Path, and 5+ years leading distributed teams. Wire transfers up to about $20M, trade booking, SWIFT, headless commerce, Stripe, and OpenID Connect SSO. I care about systems where being wrong costs money, and I bring that bar to AI. AWS Certified Generative AI Developer (Professional).