Senior GPU Runtime & HPC Software Engineer

NVIDIA; California (MO); On-site; USD 152,000 - 287,500; Full time

Job summary

NVIDIA is seeking a researcher to design, implement and maintain highly optimized communication runtimes for deep learning frameworks and HPC interfaces on GPU clusters. You will work with CUDA and Linux, contributing to MPI/OpenSHMEM and related system software to enable GPU-to-GPU and GPU-to-component interactions.

Candidate will develop proofs-of-concept, explore new programming models, and help advance hardware features while collaborating across multinational teams in a fast-paced

Qualifications

• M.S./Ph.D. in CS/CE or equivalent experience.
• 5+ years of relevant experience.
• Excellent C/C++ programming and debugging skills.
• Strong experience with Linux.
• Expert understanding of computer system architecture and operating systems.
• Experience with parallel programming interfaces and communication runtimes.
• Ability and flexibility to work and communicate effectively in a multi-national, multi-time-zone corporate environment.

Responsibilities

• Design, implement and maintain highly-optimized communication runtimes for Deep Learning frameworks (e.g. NCCL for TensorFlow/PyTorch) and HPC programming interfaces (e.g. UCX for MPI/OpenSHMEM) on GPU clusters.
• Participate in and contribute to parallel programming interface specifications like MPI/OpenSHMEM.
• Design, implement and maintain system software that enables interactions among GPUs and interactions between GPUs and other system components.
• Create proofs-of-concepts to evaluate and motivate extensions in programming models, new designs in runtimes and new features in hardware.

Skills

C/C++ programming

Linux

Parallel programming

Debugging

Communication in multinational teams

System architecture knowledge

Education

M.S./Ph.D. in CS/CE

Job description

NVIDIA is seeking a researcher to design, implement and maintain highly optimized communication runtimes for deep learning frameworks and HPC interfaces on GPU clusters. You will work with CUDA and Linux, contributing to MPI/OpenSHMEM and related system software to enable GPU-to-GPU and GPU-to-component interactions.

Candidate will develop proofs-of-concept, explore new programming models, and help advance hardware features while collaborating across multinational teams in a fast-paced