Shruti Shivakumar
Software Engineer at NVIDIA
San Jose, California, United States
Summary
🤩
Rockstar🎓
Top SchoolShruti Shivakumar is a software engineer specializing in high-performance and distributed computing, currently contributing to NVIDIA after completing a PhD in Computational Science and Engineering at Georgia Tech. With 11 years of experience, she has built GPU-accelerated C++/CUDA systems for large-scale tensor and dataframe workloads, including notable contributions to the popular rapidsai/cudf project where she optimized JSON/CSV readers and memory usage. Her research-driven background includes developing Tucker decomposition libraries for sparse tensors and scalable hypergraph algorithms for cybersecurity and scientific applications. Comfortable bridging research and production, she pairs rigorous algorithmic insight with pragmatic engineering—often squeezing performance and memory gains in constrained GPU environments. Based in San Jose, she brings both academic depth and open-source impact to teams tackling data-intensive computing problems.
11 years of coding experience
Indian Institute of Technology MadrasDoctor of Philosophy - PhD Computational Science, Doctor of Philosophy - PhD Computational Science at Georgia Institute of Technology
Github Skills (12)
cuda10
json10
gpu-programming10
cudf10
csv10
c-language10
cprogramming-language10
data-analysis9
data-structure9
data-structures9
algorithms9
data-science8
Programming languages (3)
Github contributions (5)
rapidsai/cudf
Oct 2023 - Apr 2025
cuDF - GPU DataFrame Library
Role in this project:
Back-end Developer
Back-end DeveloperContributions:431 reviews, 63 PRs, 588 comments in 1 year 5 months
Contributions summary:Shruti primarily contributed to the cuDF GPU DataFrame Library by implementing and enhancing JSON and CSV reader and writer APIs. Their work involved adding stream parameters to public APIs, incorporating new test cases, and optimizing memory usage. Furthermore, they contributed to improving the performance of JSON reader by incorporating optimizations when the mixed_types_as_string option is enabled.
cudadataframe-librarydata-analysiscppcudf
shrshi/CS6290
Feb 2018 - Apr 2018
Contributions:17 commits, 14 pushes, 1 branch in 2 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.