Senior DL/HPC Communications Architect — Equity Eligible

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity eligibility

Additional benefits

Job summary

NVIDIA Corporation in Santa Clara, CA, seeks a senior researcher to drive innovations in GPU communication for AI and HPC systems. You will prototype, model, and validate scalable interconnect technologies across CPU/GPU domains.

The role requires advanced C/C++ skills, Linux proficiency, and deep knowledge of parallel runtimes. Collaboration across time zones and teams is expected, with opportunities to influence next‑gen NVIDIA platforms.

Qualifications

• MS/PhD in CS/CE or equivalent experience.
• 5+ years of relevant experience.
• Excellent C/C++ programming and debugging skills.
• Experience with parallel programming models (MPI, SHMEM) and at least one communication runtime (MPI, NCCL, NVSHMEM, OpenSHMEM, UCX, UCC).
• Deep understanding of operating systems, computer and system architecture.
• Strong grasp of network architecture, topology, algorithms, and communication scaling for AI/HPC workloads.
• Solid experience with Linux.
• Ability to work in a multi-national, multi-time-zone environment.

Responsibilities

• Investigate opportunities to improve communication performance by identifying bottlenecks in today’s systems.
• Design and implement new communication technologies to accelerate AI and HPC workloads.
• Explore innovative HW/SW solutions for next-gen platforms as part of co-design with GPU, Networking, and SW architects.
• Build proofs-of-concept, run experiments, and perform quantitative modeling to evaluate new innovations.
• Use simulation to assess performance of large GPU clusters (hundreds to thousands of GPUs).

Skills

C/C++ programming

MPI/SHMEM

OpenSHMEM

NCCL/NVSHMEM

UCX/UCC

Linux

OS concepts

Education

MS/PhD in CS/CE

Tools

CUDA

NVIDIA GPUs

InfiniBand

RoCE

NVLink

PyTorch

TensorFlow

Job description

NVIDIA Corporation in Santa Clara, CA, seeks a senior researcher to drive innovations in GPU communication for AI and HPC systems. You will prototype, model, and validate scalable interconnect technologies across CPU/GPU domains.

The role requires advanced C/C++ skills, Linux proficiency, and deep knowledge of parallel runtimes. Collaboration across time zones and teams is expected, with opportunities to influence next‑gen NVIDIA platforms.