Semiqlassical

Semiqlassical builds high-precision physics ML infrastructure for the regime between classical and quantum simulation. The bet is simple: scientific ML should be understandable, auditable, and broadly useful — grounded in mathematics and computational science, not opaque black boxes. Our first product, Attryx, brings that idea to drug discovery.

A few principles guide the work: high precision — models that respect the math and physics of the systems they describe; no black boxes — understandable, auditable tooling that is measurable, private, and safe by design; and just better science — operable physics ML in the hands of people doing real research.

physics-informed ML  ·  quantum & classical Markov chains  ·  simulation tooling  ·  quantum-inspired optimization  ·  drug discovery

Visit semiqlassical.tech 

From academia to a startup

Before founding a company, I spent my career in research. I was an assistant professor of computer science at Missouri S&T, where my group's work was supported in part by the National Science Foundation. Earlier I was a postdoc at LSU's Center for Computation & Technology, and I earned my PhD in computer science from George Mason University under Dana Richards.

My research has wandered — by design. It started in algorithms and data structures (comparison-complexity and graph-routing models), moved through online algorithms and the \(k\)-server problem, and then pivoted to the theory of quantum computing: quantum walks and their generalizations, quantum property testing, and quantum circuit compilers. Along the way I built things — qubit routers, resource-efficient chaos generators, and HPC pipelines. Semiqlassical is where all of that finally points in one direction.

Want the details? See my research and publications, or the courses I've taught.