Vignesh Gopakumar
Visiting Research Fellow at UK Atomic Energy Authority
Oxford, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolVignesh Gopakumar is a Senior AI Research Scientist with nine years of experience applying physics-informed machine learning to accelerate and quantify uncertainty in complex numerical simulations, primarily for the fusion energy domain. At UKAEA he leads development of Neural-PDE solvers, foundation models for science, and robust surrogate models that inform simulation campaigns to maximise information gain. A physicist-turned-AI researcher with a PhD from UCL and hands-on stints at STFC, Caltech and as AI Chief at SimVue, he bridges domain physics and scalable ML engineering. Known for combining theory and applied tooling, he focuses on making scientific ML both more accurate and more actionable for downstream decision-making in fusion research.
9 years of coding experience
5 years of employment as a software developer
Master of Science - MS, European Master in Nuclear Fusion and Engineering Physics, Master of Science - MS, European Master in Nuclear Fusion and Engineering Physics at Universite de LorraineBachelor of Science - BS, Physics, Bachelor of Science - BS, Physics at Loyola CollegeMaster of Science - MS, European Master in Nuclear Fusion and Engineering Physics, Master of Science - MS, European Master in Nuclear Fusion and Engineering Physics at University of StuttgartUniversity College London
English, Malayalam, Tamil, French
Stackoverflow
143reputation
20kreached
1answer
6questions
Github Skills (46)
python10
machine-learning9
tensorflow9
deep-learning9
api8
deep-neural-networks8
ml8
neural-network8
data-science8
theano7
cryptocurrency7
solver7
hessian6
earth-science6
convolution6
Programming languages (2)
Github contributions (5)
gitvicky/tf-pde
Jun 2020 - Jan 2021
Autodiff based PDE solver implemented on the Tensorflow 2.x API. Package distribution is under the MIT License.
Contributions:1 release, 35 commits, 24 pushes in 7 months
apimit-license2-xpdepde-solver
Plasma-FNO/FNO_Multi_Blobs
Jan 2023 - Jun 2024
Fourier Neural Operator Modelling for Multi-Blob Diffusion within a Reduced MHD case built using JOREK
Contributions:47 pushes, 1 branch in 1 year 4 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.