Yashwant Singh

Senior Software Engineer at NVIDIA

Bengaluru, Karnataka, India
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Yashwant Singh is a senior software engineer and compiler specialist based in Bengaluru with three years of hands-on experience optimizing LLVM-based toolchains for GPUs and CPUs. He has driven backend improvements at AMD and contributed to Numba—an influential NumPy-aware Python compiler—by refining pass management, code generation, and optimization levels. At NVIDIA he currently focuses on squeezing performance from the Grace CPU superchip, bringing practical expertise in divergence analysis, register allocation, GlobalISel, and pass manager design. Comfortable across system software, compiler internals, and documentation, he blends low-level optimization work with clear release communication. A pragmatic problem-solver, he pairs production-grade contributions to high-profile open-source projects with a track record of shipping target-specific compiler enhancements.
code3 years of coding experience
job4 years of employment as a software developer
bookBachelor of Engineering - BE, Computer Science, Bachelor of Engineering - BE, Computer Science at Visvesvaraya Technological University
github-logo-circle

Github Skills (9)

compiler10
compiler-compiler10
numba10
python10
numpy10
llvm10
optimization10
testing9
parallel8

Programming languages (5)

TypeScriptShellC++LLVMPython

Github contributions (5)

github-logo-circle
numba/numba

Jul 2024 - Mar 2025

NumPy aware dynamic Python compiler using LLVM
Role in this project:
userBackend Developer
Contributions:5 reviews, 3 PRs, 16 comments in 8 months
Contributions summary:Yashwant primarily focused on improving the Numba compiler's internal optimization processes. Their contributions include refactoring the module pass manager creation, modifying the optimization levels, and renaming test files. Furthermore, they implemented optimizations and modifications within the `codegen.py` file, improving the compiler’s efficiency. Additionally, the user updated the documentation with release notes to inform users of the changes.
cudapythonparallelnumpynumba
yashssh/llvmlite

Feb 2024 - Mar 2025

A lightweight LLVM python binding for writing JIT compilers
Contributions:40 pushes, 14 branches in 1 year 1 month
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.
Request Free Trial
Yashwant Singh - Senior Software Engineer at NVIDIA