Arnav Goel
Software Engineer at Nvidia Corporation
San Jose, California, United States
Summary
🤩
RockstarArnav Goel is a Senior Systems Software Engineer with a decade of experience building datacenter networking, AI/ML compiler and runtime stacks, and low-level systems for accelerators. He holds an MS in Electrical Engineering from USC and a BE (Hons) from BITS Pilani, and has worked across Cisco, Oracle, SambaNova, and NVIDIA on projects spanning Nexus switches, enterprise servers, and production AI accelerators. His expertise covers compiler/runtime integration for PyTorch and TensorFlow, distributed training frameworks (Megatron, DeepSpeed, torch.distributed), PCIe/IOMMU/SRIOV device drivers, and user-space high-performance networking (RDMA, DPDK). Comfortable bridging hardware and software, he repeatedly ships fast-path communications and kernel/driver features that unlock scalable ML training and inference. Based in San Jose, he combines datacenter networking pedigree with deep accelerator and systems knowledge—often tackling the subtle OS and DMA challenges that make large-scale GPU communication reliable in production.
10 years of coding experience
Github Skills (10)
nvidia10
linux10
rdma9
cuda9
gpu8
low-level6
infiniband6
testing6
python4
cudnn4
Programming languages (3)
Github contributions (5)
agoel2012/CodeGen
Dec 2020 - Dec 2020
Contributions:19 pushes, 1 branch in 2 days
agoel2012/rdma_client_server
Jun 2023 - Jul 2023
Contributions:17 pushes, 1 branch, 1 issue in 3 days
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.