Yejin Kim is a tenured associate professor and machine learning researcher in Houston with nine years of experience applying multimodal and temporal ML to healthcare, specializing in subject segmentation and causal inference for treatment effect analysis. She has led NIH-funded projects and interdisciplinary teams to develop tensor/matrix factorization, recurrent and graph neural network models that revealed disease subtypes and improved clinical trial targeting. Her work spans from federated and interpretable tensor methods to causal trees and Bayesian networks, with measurable translational outcomes such as identified subtypes that increased trial success prospects and a $3.9M grant. A pragmatic coder and mentor, she bridges academia and deployment using PyTorch, causalML, and clinical data pipelines, and she has a track record of organizing datathons and mentoring trainees. Notably, she has delivered recommender systems and privacy-preserving factorization techniques, demonstrating a rare blend of deep theoretical methods and real-world clinical impact.
9 years of coding experience
13 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science (Machine learning), 3.89/4.3, Doctor of Philosophy - PhD, Computer Science (Machine learning), 3.89/4.3 at Pohang University of Science and Technology
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.