Building practical AI systems for software development.
I’m a software development team lead and hands-on engineer working with coding agents, local and cloud-hosted models, developer tooling, evaluations, cloud infrastructure, and the systems that help engineering teams ship better software.
What I work on
I build and evaluate the systems around AI-assisted software development: agent workflows, developer tooling, model experiments, and the guardrails that make them useful in real teams. My leadership experience shapes the work—clear evidence, honest capability boundaries, maintainable systems, and better engineering outcomes over novelty.
Learn more about my background →Selected Work
EXPERIMENTAL
AI Systems Lab
An experimental learning and evaluation environment for AI model systems, exploring local llama.cpp and cloud-hosted OpenAI-compatible providers, routing, compatibility, benchmarks, and capability boundaries.
Explore the lab →Agent Skills
Reusable, evidence-backed workflows that turn practical engineering judgment into dependable instructions for AI coding agents.
Read the case study →Why I Keep Coming Back to Codex
What customizing coding agents, building evaluations, weighing usage costs, and testing workflow continuity taught me.
Read the article →Opportunities and collaboration
I’m interested in hands-on AI/software engineering roles, engineering leadership opportunities, and collaborations around agents, evaluations, model selection, and developer tooling.
Get in Touch