Summary
Karan Shah is a Senior Software Engineer with 11 years of experience at the intersection of machine learning, physics, and large-scale simulation, now contributing to Roblox’s Physics Simulation Engine. He holds advanced training in computational science and a PhD track in computer science focused on physics-informed neural networks for quantum dynamics, combining deep learning with domain-specific simulation frameworks. His background spans research roles at national labs and academia—developing Bayesian models for cosmology, Gaussian-process gravitational-wave models, and ML-derived exchange-correlation functionals—bringing rigorous scientific modeling into production-grade systems. Comfortable in C++, Python, and ML toolchains, he blends low-level simulation know-how with modern neural approaches to accelerate physical-science workflows. Based in Dresden, he pairs a researcher’s rigor with engineering pragmatism, and maintains a public-facing portfolio at karan.sh that showcases his cross-disciplinary projects.
11 years of coding experience
10 years of employment as a software developer
Master of Science - MS Computational Science & Engineering, Master of Science - MS Computational Science & Engineering at Georgia Institute of Technology
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Technische Universität Dresden
English, Hindi, Gujarati