Summary
Benjamin Comer is an AI researcher and computational chemist with nine years of experience applying ML, GNNs, and HPC to accelerate materials and catalyst discovery. With a PhD from Georgia Tech and postdoctoral work at Stanford, he has pioneered a new subfield in photocatalytic nitrogen fixation and developed production-grade tools used across research centers. At Shell he led projects that integrated experiments and MLβpublishing papers, filing a patent, and inventing a formulation optimization algorithm roughly 1000x faster than prior methods. He is known as the go-to expert for graph neural networks in chemistry, strong communicator, and builder of reproducible pipelines from DFT to generative molecular models. Benjamin combines deep theoretical expertise (DFT, electronic-structure descriptors) with practical software craftsmanship (Python, PyTorch, HPC) and a track record of turning complex simulations into actionable experimental guidance. An uncommon strength is his ability to compress multi-day workflows into seconds through automation, enabling faster iteration between computation and lab.
9 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Chemical Engineering, Doctor of Philosophy - PhD, Chemical Engineering at Georgia Institute of Technology
Bachelor of Engineering - BE, Chemical Engineering, Summa Cum Laude, Bachelor of Engineering - BE, Chemical Engineering, Summa Cum Laude at Auburn University