Complex systems · physics · modern AI
I work on hard, unstructured problems where physical systems meet machine learning.
I have been a founding engineer on quantum-sensing hardware/software systems, and I have worked across photonics simulation, quantum dynamics, geophysical tooling, edge inference, and physics-informed ML.
I am looking for research-engineering and engineering roles around physical intelligence, automated science labs, AI4Science, Science4AI, robotics, sensing, and nontrivial technical territories with talented people.
What I have actually worked across.
The center of the site is my trajectory, not my GitHub. Repos are sketches; the stronger signal is the range of physical systems, algorithms, and research-engineering work I have already had to move through.
Founding engineer with a physics-to-systems bias.
At Dirac Labs, I worked across sensor prototyping, analog control electronics, data acquisition, firmware/middleware, algorithms, edge deployment, geophysics tools, cloud storage, and rover bringup.
I like the interplay of complex systems, physics, geometry, mathematics, and modern machine learning. I pick up new problem areas quickly and enjoy probing physical or geometric structure inside existing technical work.
I am still learning how to build things that last commercially and socially. I want to work around people who have built durable systems in fast-moving environments and can help me turn technical taste into useful incentives, products, and positive externalities.
Backstage repo notes.
These are not the main proof of fit. They are public traces of questions I was exploring, kept deliberately honest about what is finished, what is scaffolding, and what would need more work to have teeth.
Where I want to aim next.
I am most interested in teams working where modern AI has to meet physical systems, scientific instrumentation, automated labs, robotics, or new research workflows.
Working on physical intelligence, AI4Science, automated labs, or hard research engineering?
Reach out if you need someone comfortable moving through ambiguous technical territory across hardware, software, algorithms, and ML.