AI quality, model evaluation, technical product operations, and program delivery.
Technical product and operations leader with 15+ years of IT leadership and more than two years leading development of an automotive retail management platform. My work spans AI model evaluation, product strategy, quality systems, systems integration, and release operations across browser, backend, data, and mobile products.
- AI model-behavior testing and evaluation design
- Product strategy, requirements, UAT, and quality systems
- Technical program delivery and release readiness
- Cross-layer root-cause investigation across interface, backend, data, and mobile systems
- Evidence synthesis and decision-ready technical writing
-
Automotive Retail Management Platform More than two years leading an end-to-end platform spanning acquisition, CRM, inventory, pricing, listing, sales, transaction, and communications workflows across browser, backend, and iOS systems, supported by 3,788 commits, 87 automated test files, and 304 investigation and decision notes.
-
Controlled LLM Evaluation A controlled LLM evaluation using fixed-prompt trials, matched controls, and reasoning-path classification to expose a construct-validity flaw that could cause a benchmark to mislabel coherent responses.
-
AI Quality, Technical Product, and Operations Portfolio Case studies covering AI evaluation, automotive retail platform leadership, e-commerce workflow automation, quality systems, and cross-platform product operations.
I turn ambiguous operational problems into defined product behavior, traceable evidence, testable requirements, and dependable releases. My strongest work combines product judgment with hands-on investigation across interfaces, services, data, and real user workflows.
Based in the San Francisco Bay Area, with experience spanning IT leadership, product operations, technical research, and quality-focused product development.