Hugh Flournoy Van Deventer V

AI Research & Engineering

Data Science Master’s student at Harvard SEAS with a background in Math, Physics, and CS from the University of Michigan. I’m interested in the connections between physics and AI/ML, especially through the lens of complex systems, and in applying these ideas to build safer, more interpretable AI systems.

At Michigan, I was a Data Science Fellow at the Center for Academic Innovation, where I developed ExploreBlue, a course recommendation system using LLMs and semantic search under the guidance of Prof. August Evrard and Dr. Mark Mills. I also served as a peer advisor for the Physics Department.

This summer, I worked as an AI/ML Engineering Intern at Honeywell, where I worked on AI and classical image processing techniques to automatically extract building layouts from floor plans and generate cost estimates for corporate facility projects. I also built a vibration analysis system that autonomously diagnoses equipment faults by combining signal processing with LLM reasoning.

Previously, I was an ML Research Intern at Michigan Tech Research Institute, where I worked on ML methods for accelerating inverse problem solving in imaging with the goal of real-time super resolution under the guidance of Dr. Joel LeBlanc, and at Neurabuild in South Africa, where I developed ML solutions for astronomical site assessment and satellite tracking for the Astrosite project under the guidance of Prof. Gregory Cohen.