Aditya Agrawal
Senior Software Engineer at Google
San Jose, California, United States
Summary
👤
Senior🎓
Top SchoolAditya Agrawal is a Senior Software Engineer in San Jose with six years focused on deep learning performance, profiling, and computer architecture across industry leaders like Google and NVIDIA. He specializes in ML numerical and statistical analysis, model quantization, and lossless optimizations, and has driven TensorFlow graph pattern detection and profiling tools as well as CPU/GPU inference and training performance wins. At NVIDIA he helped secure MLPerf victories and created PyProf for PyTorch GPU analysis, showing a rare blend of research rigor (PhD-level ECE) and production-grade tooling. Comfortable across hardware-software boundaries, he has a background in DRAM research and PDK engineering that informs pragmatic performance trade-offs others might miss.
7 years of coding experience
12 years of employment as a software developer
Indian Institute of Technology BombayUniversity of Illinois Urbana-Champaign
English, Hindi, Chinese
Github Skills (32)
translation9
pytorch9
python9
speech-synthesis9
drug-discovery9
profiling9
tensorflow9
gpu9
deep-learning9
forecasting9
forecast9
nlp8
computer-vision8
paddlepaddle8
jax8
Programming languages (3)
Github contributions (5)
adityaiitb/pyprof2
Oct 2019 - May 2021
PyProf2: PyTorch Profiling tool
Contributions:2 PRs, 17 pushes, 1 branch in 1 year 7 months
profilingpytorchnvidia-gpudeep-learningperformance-analysis
adityaiitb/PyProf
May 2021 - Jun 2021
A GPU performance profiling tool for PyTorch models
Contributions:17 commits, 18 pushes, 5 branches in 7 days
gpuprofilingpytorch
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.