Summary
Teeratorn Kadeethum is a Principal Research Scientist with a decade of experience at the intersection of finite element methods, scientific machine learning, and emerging quantum-enabled computing for energy and subsurface applications. He has led teams at Sandia and Microsoft to deliver production-grade neural operators, PINNs, and multi-agent ML systems that cut training times from weeks to hours, enabled 97% event prediction accuracy, and generated field-validated models with sub-1% error. Currently architecting multi-agent AI and physics-driven digital twins for Siemens Energy, he blends deep domain expertise in PDE solvers and finite-volume/element discretizations with cutting-edge generative and self-supervised techniques. Notably, he has a track record of securing multi-hundred-thousand-dollar research budgets and translating advanced research—like graph-attention classifiers for orphan well detection—into high-recall field trials. Based in Florida, he pairs a PhD in applied mathematics/computer science with hands-on engineering across C++, Python, and HPC workflows to move models from theory to operational impact.
10 years of coding experience
15 years of employment as a software developer
Master of Science (MSc) Petroleum Engineering, Master of Science (MSc) Petroleum Engineering at University of Calgary
Technical University of Denmark
Bachelor of Engineering (BEng) Mechanical Engineering, Bachelor of Engineering (BEng) Mechanical Engineering at Chulalongkorn University
English, French, Chinese