Summary
Kathryn Kirchoff is an investigator in cheminformatics at GSK with a PhD in computer science from UNC-Chapel Hill and eight years of experience applying machine learning to drug discovery. Her work spans contrastive and generative methods, transformer and autoencoder architectures, representation learning, and practical QSAR approaches for noisy, real-world molecular data. She has transitioned academic deep-learning research—ranging from out-of-distribution detection to ultra-fast similarity-based virtual screening—into industry-facing cheminformatics solutions. Kathryn’s background includes postdoctoral and multiple graduate research roles under leaders in molecular modeling and network medicine, plus ML internships at MilliporeSigma and insitro. Beyond algorithms, she emphasizes data curation and robustness when working with messy biochemical datasets—a skill often overlooked in academic prototypes. Outside work, she trains Brazilian jiu jitsu, reflecting a competitive, disciplined approach to research and problem solving.
8 years of coding experience
6 years of employment as a software developer
Bachelor's degree with Honors Biology, Bachelor's degree with Honors Biology at Virginia Commonwealth University
Non-degree seeking Computer Science, Non-degree seeking Computer Science at Virginia Commonwealth University - College of Engineering
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of North Carolina at Chapel Hill