About
I'm an AI engineer working on agent systems and the evaluation harnesses around them. I build things, measure whether they work, and write about what I learn.
What I work on
- Agent systems: multi-agent orchestration, tool use and MCP, human approval or dry runs before writes
- Harnesses and evals: a baseline and eval set before the first model call, trace evals, retrieval metrics (MRR, NDCG, Recall@K)
- Client-facing delivery: requirements through production handover
How I approach problems
Every project starts with the same questions:
- What does success look like? (Define the metric)
- Where are we now? (Measure the baseline)
- What changed? (Prove the delta)
This isn't revolutionary. It's just discipline. But it's the difference between "I think this works" and "here's the evidence."
Background
I spent 15+ years in enterprise consulting (MarkLogic, Oracle, RightNow), leading technical delivery across APAC and North America. I translated business requirements into working systems for banks, telcos, and government agencies, and managed international teams doing the same.
Now I'm applying that lens to AI engineering. I build agent systems, and the eval harnesses that tell you whether an LLM actually works before it reaches production. My projects emphasize measurable outcomes over demos: trace evals, measured baselines, failure-mode analysis.
I'm not coming from a research background. I'm coming from delivery, where things need to work reliably, at scale, for real users. That turns out to be exactly what's missing in most LLM deployments.
Taking on consulting engagements, and open to Forward Deployed Engineer or AI Solutions Engineer roles. Client-facing work on agent systems, harnesses and evaluation. Remote, available now.