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

This role focuses on designing and implementing high-performance, low-latency GPU-aware networking paths for intra-node communication within HPE's edge-to-cloud computing solutions. The position involves optimizing data movement between GPUs and NICs, integrating with major GPU ecosystems like NVIDIA CUDA and AMD ROCm, and enhancing open-source communication stacks. The engineer will lead upstream contributions, drive architectural decisions, and mentor senior team members to deliver innovative HPC and AI solutions.