Harrison develops Bayesian inference methods that combine generative models with sparse measurements to quantify geological uncertainty. He earned his PhD in Aeronautics and Astronautics at Stanford University with the Stanford Intelligent System Lab (SISL), where he researched Bayesian inference and generative modeling to evaluate the safety of complex autonomous systems and collaborated with NASA JPL, Ford, Motional, and Nissan. His industry experience includes risk quantification for physical AI, and autonomous decision making and safety validation in robotics and aerospace applications. In his spare time, he enjoys running, birding, and tinkering on side projects.