Nao Hiranuma is Director of Machine Learning Research and scientific co-founder at Vilya, bringing 11 years of deep-learning and computational biology experience to deploy geometric generative models and ML operations. He holds a PhD from the University of Washington’s Allen School and built DeepAccNet, which won CASP14’s Estimation of Model Accuracy against 68 teams, demonstrating rare expertise at the intersection of protein structure and ML. His work spans GNNs, SE(3)-equivariant transformers, 3D convnets and large-scale training pipelines on Slurm, and he’s transitioned academic models into production at Vilya. A hands-on implementer, he routinely re-implements state-of-the-art papers in PyTorch/TensorFlow and optimizes performance across millions of samples. Based in Seattle, he balances research leadership with practical ML engineering, advising how advanced geometric and model-based optimization methods can drive real-world protein design applications.
11 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Computer Science, Doctor of Philosophy (Ph.D.), Computer Science at University of Washington
Bachelor of Arts (BA) in Biology, Bachelor of Arts (BA) in Computer Science, 3.8 GPA, Bachelor of Arts (BA) in Biology, Bachelor of Arts (BA) in Computer Science, 3.8 GPA at Carleton College
Contributions:17 commits, 19 pushes, 1 branch in 4 days
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.
Request Free Trial
Nao Hiranuma - Director Of Machine Learning Research at Vilya