see ya space cowboy...
I build tools for understanding, testing, and improving complex software systems.
My work connects real-time grid-state coordination at Tarigma, production HPC authentication tracing at Ohio Supercomputer Center, and typed AI evaluation and execution in Attune and SearchBench. Across those domains, I use explicit representations, constrained interfaces, and repeatable experiments to understand behavior and measure improvements.
I’m seeking a mid-level individual-contributor role in AI systems or developer infrastructure, combining independent technical work with delivery on a production engineering team.
Attune source · How Attune works · SearchBench
My experiments include modifying llama.cpp embedding execution and investigating DSPy executable-program optimization. Typed contracts, compiler feedback, and repeatable tests help me decide which optimizations are safe and useful.
Presented SearchBench at AI Tinkerers Columbus in June 2026; featured as a Community Favorite in Top AI Demos #31.
I'm especially interested in small, technically ambitious teams working on developer tools, build systems, code intelligence, AI infrastructure, evaluation, or research-heavy software. I do my best work when the problem is still a little strange and the right abstraction has not been decided yet.
Typical themes: opaque software and infrastructure, security boundaries, developer tooling, and AI-agent workflows — made easier to inspect, debug, and trust.
Small, bounded work tends to fit best: diagnostics, internal tools, repo or CI cleanup, observability hooks, eval or reporting passes, dashboards, or documentation that makes a system legible.
Developer tools & build systems. Fast feedback loops, build graphs, reproducible environments, CI, code search, repository interfaces, and tooling that makes large software systems easier for humans and agents to operate.
AI systems & verification. Coding agents, eval harnesses, deterministic supervision, repository-specific behavior, and systems for turning model output into evidence you can actually inspect and trust.
Research engineering. I like taking an odd technical question, building the smallest instrument that can answer it, running the experiment, and following the result even when it kills the original hypothesis.
I'm primarily looking for a full-time engineering role, but I'm also open to unusually interesting focused projects.
If you are not sure how to scope something, describe the system and what feels unclear — we can pick a narrow first slice.
My Background.
Search through my back catalog.
Code localization, small embedding models, and the economics of understanding a repository.
I adopted Buck2 for code generation. It gradually ate remote execution, experiment tracking, and workflow orchestration.
Turning accepted code edits into executable hypotheses, freezing them, and testing whether they can reproduce changes developers make in the future.
I build tools for understanding, testing, and improving complex software systems.
My work connects real-time grid-state coordination at Tarigma, production HPC authentication tracing at Ohio Supercomputer Center, and typed AI evaluation and execution in Attune and SearchBench. Across those domains, I use explicit representations, constrained interfaces, and repeatable experiments to understand behavior and measure improvements.
I’m seeking a mid-level individual-contributor role in AI systems or developer infrastructure, combining independent technical work with delivery on a production engineering team.
Attune source · How Attune works · SearchBench
My experiments include modifying llama.cpp embedding execution and investigating DSPy executable-program optimization. Typed contracts, compiler feedback, and repeatable tests help me decide which optimizations are safe and useful.
Presented SearchBench at AI Tinkerers Columbus in June 2026; featured as a Community Favorite in Top AI Demos #31.
I'm especially interested in small, technically ambitious teams working on developer tools, build systems, code intelligence, AI infrastructure, evaluation, or research-heavy software. I do my best work when the problem is still a little strange and the right abstraction has not been decided yet.
Typical themes: opaque software and infrastructure, security boundaries, developer tooling, and AI-agent workflows — made easier to inspect, debug, and trust.
Small, bounded work tends to fit best: diagnostics, internal tools, repo or CI cleanup, observability hooks, eval or reporting passes, dashboards, or documentation that makes a system legible.
Developer tools & build systems. Fast feedback loops, build graphs, reproducible environments, CI, code search, repository interfaces, and tooling that makes large software systems easier for humans and agents to operate.
AI systems & verification. Coding agents, eval harnesses, deterministic supervision, repository-specific behavior, and systems for turning model output into evidence you can actually inspect and trust.
Research engineering. I like taking an odd technical question, building the smallest instrument that can answer it, running the experiment, and following the result even when it kills the original hypothesis.
I'm primarily looking for a full-time engineering role, but I'm also open to unusually interesting focused projects.
If you are not sure how to scope something, describe the system and what feels unclear — we can pick a narrow first slice.
see ya space cowboy...
My Background.
Search through my back catalog.
Code localization, small embedding models, and the economics of understanding a repository.
I adopted Buck2 for code generation. It gradually ate remote execution, experiment tracking, and workflow orchestration.
Turning accepted code edits into executable hypotheses, freezing them, and testing whether they can reproduce changes developers make in the future.