Nima Shoghi is an ML PhD student and research engineer at Georgia Tech with a decade of experience building and deploying large-scale deep learning systems for scientific discovery and engineering. He has driven state-of-the-art work across protein dynamics, molecular property prediction, and efficient diffusion models—delivering major accuracy gains and massive speedups (20–1000x) in production-style pipelines. Technically fluent in PyTorch, JAX, CUDA/Triton, and distributed HPC training, he designs SE(3)-equivariant architectures, custom kernels, and robust fine-tuning strategies for pre-trained GNNs. His background spans both hardware-aware model compression and generative modeling (VAEs, GANs, DDPMs, autoregressive LMs), enabling cross-domain transfer and multi-modal integration. Notably, his foundation model for protein molecular dynamics extrapolates microsecond trajectories far beyond training data and scales to 1000+ residue proteins without cubic memory blowup.
10 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Georgia Institute of Technology
High School Diploma, International Baccalaureate Diploma, High School Diploma, International Baccalaureate Diploma at Druid Hills High School
Contributions:80 releases, 111 commits, 106 pushes in 2 years 3 months
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.