About
I build machine learning systems that work in physical engineering. My PhD at Carnegie Mellon focused on process monitoring for metal additive manufacturing, and at Relativity Space I built computer vision and anomaly detection models for 3D-printed rocket production. Most recently I co-founded Polymath AI, leading the engineering team to build agents that automate 3D CAD workflows. I’m most interested in making AI agents reliable enough for work where mistakes are expensive, through evaluation, verification, and systems that experts can inspect and trust.
Previously: Relativity Space (ML Scientist) · NASA Marshall · Autodesk. Ph.D., Carnegie Mellon.
Areas of expertise
LLM agents
MCP and tool use
evals
ML for engineering
computer vision
additive manufacturing
Selected publications
- Process mapping for laser hot wire additive manufacturing of Ti6Al4V
- Inference of highly time-resolved melt pool visual characteristics and spatially-dependent lack-of-fusion defects in laser powder bed fusion using acoustic and thermal emission data
- Melt pool level flaw detection in laser hot wire directed energy deposition using a convolutional long short-term memory autoencoder
- Flaw detection in metal additive manufacturing using deep learned acoustic features
Full list on Google Scholar.