Kevin Song
AI Scientist at AWS
I work on machine learning systems at AWS, where I've led sports analytics initiatives with the NFL and NBA and delivered $20M+ enterprise ML projects. Before AWS, I was a computer vision engineer for the Atlanta Braves and hold a PhD in biophysics from the University of Chicago.
Publications
Peer-Reviewed
-
Song, K. C. (2026). PlayGenMoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction. CVPRW 2026.
-
Song, K. C., Diewald, E., Boomhower C., et al. (2026). Decoding Defensive Coverage Responsibilities in American Football Using Factorized Attention Based Transformer Models. ISACE 2026. [Link]
-
Song, K. C., Molina, A. V., Chen, R., et al. (2021). Folding and misfolding of potassium channel monomers during assembly and tetramerization. PNAS, 118(34), e2103674118. [Link]
-
Wu, E. L., Cheng, X., Jo, S., …, Song, K. C., et al. (2014). CHARMM-GUI membrane builder toward realistic biological membrane simulations.
-
Wu, E. L., Qi, Y., Song, K. C., et al. (2014). Preferred orientations of phosphoinositides in bilayers and their implications in protein recognition mechanisms. J. Phys. Chem. B, 118(16), 4315–4325.
-
Jo, S., Song, K. C., Desaire, H., et al. (2011). Glycan Reader: automated sugar identification and simulation preparation. J. Computational Chemistry, 32(14), 3135–3141.
-
Song, K. C., Livanec, P. W., Klauda, J. B., et al. (2011). Orientation of fluorescent lipid analogue BODIPY-PC to probe lipid membrane properties. J. Phys. Chem. B, 115(19), 6157–6165.
AWS Blog Posts
Improving NFL player health using machine learning with AWS Batch [Link]
Analyze and visualize multi-camera events using Amazon SageMaker Studio Lab [Link]
Deploying and benchmarking YOLOv8 on GPU-based edge devices using AWS IoT Greengrass [Link]
Hosting YOLOv8 PyTorch models on Amazon SageMaker Endpoints [Link]
Scale YOLOv5 inference with Amazon SageMaker endpoints and AWS Lambda [Link]
Projects
Coming soon.
Blog
Coming soon.