About

I'm the founder of Meronymy, where I'm building AI systems for making expertise more scalable, auditable, and operationally useful. My work sits at the infrastructure and applied layers of intelligent systems: agent orchestration, tool use, retrieval and context systems, evaluation, observability, and ML infrastructure. Before Meronymy, I built and operated high-throughput data infrastructure for production genomics — pipeline orchestration, workflow automation, and large-scale monitoring of long-running systems.

My core interest is scaling expertise: building systems that help complex knowledge move through real workflows with more structure, provenance, and trust. I'm especially interested in AI systems that don't just generate answers, but coordinate work, surface uncertainty, preserve context, support human review, and make decision-making easier to audit.

I favor explicit contracts over implicit assumptions, and systems designed to be understood, not just built. I'm drawn to novel complexity when it solves real problems, but I'm skeptical of complexity that exists to be clever. When evaluating trade-offs, I lean toward approaches that make failure visible, keep debugging tractable, and leave room for the next engineer to reason about the system without needing its original author.

Long term, I want to work on the systems and infrastructure that make AI reliable at scale. I'm especially drawn to ML infrastructure, agent systems, AI reliability, evaluation platforms, data infrastructure, and applied AI products for complex domains.