Kumar Shridhar is a PhD candidate at ETH Zürich with nine years of experience building machine learning and NLP systems. He blends research rigor with hands-on engineering, contributing practical Bayesian deep learning implementations such as a PyTorch Bayesian CNN library that applies Bayes by Backprop. Based in Zurich, he focuses on backend development and model implementation, refactoring codebases to improve structure and reproducibility. His work suggests a knack for translating probabilistic ML research into maintainable, production-ready code. Colleagues can expect a researcher-engineer who balances theoretical depth with pragmatic software practices.
Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.
Role in this project:
Back-end Developer & ML Engineer
Contributions:221 commits, 11 PRs, 196 pushes in 2 years 6 months
Contributions summary:Kumar made changes to the file structure and refactored code within the repository. They also added several Bayesian Convolutional Neural Network models in PyTorch, indicating a focus on implementing and modifying machine learning models. These changes demonstrate involvement in backend code development, as well as implementing ML models based on Bayes by Backprop.
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.