Sharan Chetlur
Director Of Engineering at NVIDIA
United States
Summary
🤩
Rockstar🎓
Top SchoolSharan Chetlur is a director-level engineering leader with 7 years of documented experience delivering high-performance software for AI and HPC at NVIDIA and Cerebras Systems. He has progressed from technical lead on cuDNN/cuBLAS primitives to senior engineering roles optimizing deep learning frameworks and LLM serving across GPU and datacenter scales. At Cerebras he led a 35-engineer kernels team building foundational operations for wafer-scale processors, and at NVIDIA he has driven MLPerf benchmark submissions and end-to-end model performance work. Sharan blends deep systems and algorithmic expertise (including GPU sparse direct methods) with hands-on leadership that aligns research-grade optimizations to production datacenter needs. He is based in the United States and known for scaling teams and codepaths that turn low-level primitives into measurable system-level gains. An understated through-line in his career is consistently translating specialized numerical and GPU research into deployable, high-throughput serving infrastructure.
7 years of coding experience
16 years of employment as a software developer
BITS Pilani, Birla Institute of Technology and ScienceUniversity of Florida
Github Skills (7)
mixture-of-experts10
pytorch10
ray10
pytorch-lightning10
temporal-data10
distributed-training9
deep-learning9
Programming languages (1)
Github contributions (1)
NVIDIA/apex
Nov 2018 - Jun 2020
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Contributions:4 commits, 3 PRs, 4 pushes in 1 year 7 months
pytorchraymixed-precisiondeep-learningtemporal-data
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.