Rajneesh Bhardwaj - Principal System Architect at AMD

Rajneesh Bhardwaj

Principal System Architect at AMD

Canada

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Rajneesh Bhardwaj is a Principal System Architect at AMD driving exascale GPU and AI infrastructure design with over two decades of cross-stack expertise from firmware to cloud orchestration. He architects rack- and pod-scale multi-GPU systems, coherent CPU–GPU interconnects, and unified memory models—work that contributed to MI300A and the El Capitan exascale system—and pioneered the industry’s first GPU-based checkpoint/restore solution to cut cloud downtime and costs. A long-time Linux kernel maintainer and ROCm contributor, Rajneesh brings production-grade open source engineering to low-level device integration, including extending CRIU to support AMD GPU memory management. Formerly a power management architect at Intel, he combines systems research with hands-on implementation of RDMA, virtualization, and confidential computing features. Based in Toronto, he’s known for translating cutting-edge research into deployable, high-impact infrastructure innovations.

9 years of coding experience

18 years of employment as a software developer

Bachelor of Technology - BTech, Electronics, Bachelor of Technology - BTech, Electronics at Galgotias College of Engineering and Technology

Kendriya Vidyalaya Sangathan

B Tech, Electronics, B Tech, Electronics at Uttar Pradesh Technical University

English, Hindi

Github Skills (16)

kernel10

plugin-development10

c1710

c1110

linux-kernel10

driver9

protobuffer9

protobuf9

system-programming9

device-driver9

memory-management9

checkpointing7

container7

re-store7

checkpoint7

Programming languages (2)

CPython

Github contributions (5)

checkpoint-restore/criu

Apr 2021 - Dec 2021

Checkpoint/Restore tool

Role in this project:

Back-end Developer

Contributions:38 reviews, 7 commits, 6 PRs in 8 months

Contributions summary:Rajneesh primarily contributes to the CRIU (Checkpoint/Restore tool) project, focusing on extending its functionality to support AMD GPU devices and their memory management via the KFD kernel driver. This involves introducing new plugin hooks for handling device file VMAs, updating VMA maps, and late-stage device resume operations. The user implements AMD ROCm support by developing an amdgpu plugin which uses protobuf to serialize and save the amdkfd data. The user's contributions include supporting sDMA-based buffer access and initializing the AMD KFD header within the plugin.

containerszero-downtimesuspendcheckpointcriu

rajbhar/linux

May 2021 - May 2021

Linux kernel source tree

Contributions:18 pushes, 3 branches in 1 day

kernelkernel-sourcelinuxlinux-kernelmanual

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