📢 New: get today's jobs on our WhatsApp Channel
Jobiglo

No results.

Principal Engineer - Scale-Up GPU Networking (HPC / AI)

hpe · Bengaluru

New
Hybrid Senior 🇬🇧 English
CUDA ROCm NVLink NCCL RCCL Libfabric UCX SHMEM OpenMPI RDMA PCIe NUMA eBPF Nsight

Job description

About the role

Hewlett Packard Enterprise's High Performance Computing, AI and Labs team is hiring a Principal Engineer for scale-up GPU networking in Bengaluru. The role is hybrid, with about two days per week spent in an HPE office. It focuses on GPU-aware networking paths, GPU memory models and communication stacks for high-bandwidth, low-latency intra-node communication.

Key responsibilities

  • Design and implement GPU-aware networking paths and optimize GPU to NIC to GPU data movement, shared memory models and DMA pathways.
  • Integrate and optimize scale-up communication with NVIDIA CUDA, NVLink, NCCL, AMD ROCm, InfinityFabric and RCCL teams.
  • Improve DMA engines, BAR mappings, ATS/IOMMU and GPU memory registration workflows.
  • Extend Libfabric, UCX, CXI, SHMEMX and OpenMPI for GPU-accelerated scale-up workflows, and optimize communication collectives, transport layers and GPU-direct capabilities.
  • Tune multi-NIC per socket, NUMA-zone mapping, GPU locality, CQ/queue design and CPU/GPU topology.
  • Lead upstream contributions to open-source projects (OFI, UCX, OpenMPI, RCCL/NCCL) and partner with HPC/AI teams on future architectures.
  • Debug across driver, runtime, GPU, kernel and user space, and build profiling workflows with Nsight, ROCm tools, eBPF and perf.

Required profile

  • 10-15+ years building high-performance networking, GPU or kernel-level software.
  • Proven experience driving architecture and cross-org technical decisions and upstream contributions.
  • Ability to mentor senior engineers, influence multi-team designs and own end-to-end delivery.

Required skills

  • C/C++, Linux internals, memory management, RDMA, PCIe, IOMMU, ATS, DMA engines.
  • CUDA, ROCm, GPU memory models, P2P, GPUDirect Storage and GPUDirect RDMA.
  • Hands-on experience with MPI, SHMEM, Libfabric, UCX or similar stacks.
  • Preferred: NIC architecture (CXI, RoCE, InfiniBand, Slingshot, NVLink Switch), collective optimization (AllReduce/AllGather), open-source HPC/AI library contributions, NUMA tuning and multi-accelerator systems.

What we offer

  • Benefits supporting physical, financial and emotional wellbeing.
  • Programs for personal and professional development.
  • An inclusive workplace with flexibility to manage work and personal needs.

Questions fréquentes

Le salaire n'est pas communiqué publiquement par le recruteur. Vous pouvez postuler et négocier directement avec hpe.
Cliquez sur "Postuler maintenant" en haut de la page. Vous pouvez importer votre CV en 1 clic — Jobiglo extrait automatiquement vos informations et postule pour vous.
Source : ats:workday

Why are you reporting this job?

Thank you for your report. We will review this job.

Explore further

Salaries, guides and searches in India.

Apply in 30 seconds

Enter your email to apply. An account will be created automatically.

Apply now →

By continuing, you accept our terms of use.

Already have an account? Login

A question about this job?

Ask it here: you will get the full job summary by e-mail, right away.

Published 3 hours ago

Expires 1 month from now

8 views · 0 interested

Boost your chances

Upload your CV — we will match you with relevant openings.

Analyzing your CV...

hpe

Bengaluru