I build AI products that hold up in real workflows.
13+ years across software delivery, technical training, data & AI consulting, and product leadership. Most recently leading product and engineering for AI hiring systems: assessments, candidate screening, and conversational interviews.
Production AI systems
Enterprise Skills Assessment Platform
Coding and data-science assessments, source-code verification, remote proctoring, and analytics across a 500+ skill library.
ProductionAI-Assisted Candidate Screening
Embedding search and LLM ranking for JD–CV matching, with context-aware question generation and structured reports.
ProductionConversational Interviewing System
Agentic multi-turn interviews with dynamic follow-ups, live coding support, and LLM-generated insights for reviewers.
15+ proofs of concept
Three working principles
Workflow fit before model cleverness
An AI feature that wins the demo can still fail in daily use. I judge it by whether it makes someone’s work meaningfully easier.
Prove it small, then productise
I validate ideas as proofs of concept before committing a roadmap, and carry the ones that hold up into production.
Platform judgement
Knowing when to build a reusable capability and when to deliver a targeted customisation matters as much as the technology.
Recent writing
Building something with applied AI?
I’m open to conversations with founders, technology leaders, and teams working on AI products.