AI systems engineer · previously Dirac Labs
I build software for noisy real-world data.
From quantum-sensing pipelines and signal processing to reproducible model-serving experiments, I turn ambiguous research problems into measurable working systems.
Three projects that make the case.
Each entry states what was hard, what I built, what evidence exists, and where the claim boundary still is.
Engineer for AI systems that touch the physical world.
Previously at Dirac Labs, I worked on quantum sensing systems: signal processing, calibration, geophysical analysis, field and aerial data workflows, and real-time inference pipelines for magnetic navigation and detection.
I build AI systems for noisy, physical-world data. My background spans physics, scientific computing, sensing, model evaluation, and hands-on hardware workflows.
Today I am focused on two areas: reliable ML infrastructure and intelligent systems that interact with sensors, hardware, or the physical world.
Other current work.
Smaller or less mature projects stay here so they do not visually compete with validated flagship work.
Questions I am actively working through.
If you are thinking about one of these, I would probably enjoy comparing notes.
Interested in AI systems, sensing, or physical-world ML?
Email me about research-engineering roles, technical collaborations, and conversations around the experiments above.