I build products end to end, then turn repeated complexity into systems teams can scale.
Four systems showing end-to-end ownership, reusable architecture, and measurable product and engineering outcomes.
04 systems · selected proofMIT
Designed and published the TypeScript and Node.js package, CLI, MCP runtime, coding-agent integrations, CI/CD, and release gates.
Durable context and specification-driven verification constrain coding-agent drift across long-running work.
Released as open-source MIT tooling with automated tests and gated publishing.
2–4×
Built the product across controlled LLM querying, crawling, analytics, scoring, deployment, and operations.
Connects page-level evidence to model-response drift and AI visibility monitoring.
Operates at <10 ms p95 and improved AI mention coverage 2–4× in controlled deployments.
cross-framework
Extracted complex e-signature flows into standalone, versioned libraries consumed by multiple applications.
Exposed framework-agnostic Web Components through stable APIs for incremental migration.
Reduced duplicate implementation and decoupled product flows from any one JavaScript framework.
+17%
Independently upgraded product-page templates and remediated technical SEO issues using RankLabs.
Combined product-template changes, structured technical fixes, and measurement across search and tracked LLMs.
Within two months, organic traffic rose 17%, tracked LLM visibility improved 43%, and AI referral share grew from 0.1% to 8% of external human sessions.
Practical writing on product systems, structured data, AI retrieval, and the controls that keep software reliable in production.
AI visibility depends on a second interface assembled by crawlers, answer engines, and agents. I call it the shadow interface, and propose a testable funnel for evaluating it.
ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews each parse JSON-LD differently. The deltas matter. Here's what I've measured running the same @graph through all five.
Field-level JSON-LD bugs that fail silently across 45K+ PDP catalogs. Each one mapped to the rich result it kills, the AI engine that drops you, and the dollar cost I model for clients.
I am considering Senior, Staff, and Principal roles where I can ship across the stack, improve the frontend platform, and build reliable AI-assisted engineering systems.
direct email · no scheduling gate