About

16 years as a backend software engineer. For the past 4 years, focused on healthcare — behavioral health, digital health, and health tech — where the infrastructure problems are harder, the compliance requirements are real, and the cost of getting it wrong is higher. Recently focused on the infrastructure side of AI — building the LLM platforms, evaluation pipelines, and internal developer tooling that production AI applications run on.

I've seen what happens when teams try to ship AI products on infrastructure that wasn't designed for it. Observability gaps that only show up under load. Prompt pipelines that break when a model is updated. Engineering teams spending months rebuilding the same foundation across projects.

Healthcare adds another layer of complexity. PHI handling, auditability requirements, and the compliance overhead that comes with any regulated environment — these aren't afterthoughts you can bolt on later.

I work with healthcare engineering teams that have serious AI ambitions and need the infrastructure layer built right. The engagement model is flexible — I can work alongside your existing team, lead the infrastructure buildout, or help you think through an architecture decision before you commit to it.

Based in San Francisco.