Soumya Vasisht
Senior Data Scientist
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolSoumya Vasisht is a Senior Data Scientist at Pacific Northwest National Laboratory specializing in constrained optimization and deep learning for system design, identification, and intelligent control of dynamical systems. With a PhD from the University of Washington’s RAIN Lab, she blends rigorous robotics and optimal control foundations with probabilistic modeling and reinforcement learning to improve navigation, planning, and state estimation for autonomous systems. Her work spans model-based and model-free approaches, Bayesian optimization, multi-fidelity modeling and uncertainty quantification, enabling principled trade-offs between performance and safety. Having progressed from postdoctoral research to research scientist and now senior data scientist at PNNL, she brings both academic depth and applied systems experience to complex, safety-critical control problems. An engineer at heart, she often couples deterministic control theory with modern ML pipelines to produce interpretable, deployable solutions for real-world autonomy.
3 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy - PhD, Aeronautics and Astronautics, Robotics, Optimization and Control, Doctor of Philosophy - PhD, Aeronautics and Astronautics, Robotics, Optimization and Control at University of WashingtonBachelor of Engineering - BE, Information Science and Engineering, Bachelor of Engineering - BE, Information Science and Engineering at PES University
English, Kannada, Hindi, German
Github Skills (14)
constrained-optimization10
nonlinear-optimization10
dynamical-systems10
predictive10
nonlinear-dynamics10
system-identification10
model-predictive-control9
control-systems9
differentiable-programming8
pytorch8
parametric8
optimization8
physics8
deep-learning7
Programming languages (1)
Github contributions (1)
pnnl/neuromancer
Jan 2023 - Nov 2023
Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.
Contributions:1 PR, 1 branch, 2 issues in 9 months
nonlinear-optimizationdynamical-systemsproblemsmodel-predictive-controldifferentiable-programming
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.