Navyaa Sanan
Senior Software Engineer, Generative AI
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolNavyaa Sanan is a Senior Software Engineer specializing in generative AI at NVIDIA with three years of professional experience and a strong academic foundation in Computer Science and Statistics from UIUC (Highest Distinction). She authored ComputeEval, an open-source framework for evaluating LLMs on CUDA, demonstrating a practical focus on performance and tooling for large models. Her background includes multiple internships and teaching assistant roles that reflect both hands-on engineering and mentorship in academic settings. Based in Seattle, she combines deep systems and ML engineering skills with a knack for turning research-grade ideas into developer-facing tools that scale.
3 years of coding experience
3 years of employment as a software developer
Senior Secondary Program, Wearable Technologies and the internet of things, A, Senior Secondary Program, Wearable Technologies and the internet of things, A at Harvard UniversityBachelor's degree, Computer Science and Statistics, 3.86, Highest Distinction, Bachelor's degree, Computer Science and Statistics, 3.86, Highest Distinction at University of Illinois Urbana-Champaign
English, Hindi
Github Skills (13)
visual-studio-code10
typescript10
electron10
microsoft10
editor10
vscode-extension9
visual-studio-code-extension8
vscode7
cpp5
code-generation5
debugging5
cuda4
large-language-models3
Programming languages (3)
Github contributions (5)
NVIDIA/compute-eval
Apr 2025 - Oct 2025
Evaluating Large Language Models for CUDA Code Generation ComputeEval is a framework designed to generate and evaluate CUDA code from Large Language Models.
Contributions:1 push in 5 months
code-generationcudalarge-language-models
NVIDIA/nsight-vscode-edition
Mar 2023 - Jun 2024
A Visual Studio Code extension for building and debugging CUDA applications.
Contributions:26 comments, 15 issues in 1 year 3 months
cudadebuggingvisual-studio-code-extension
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.