Skip to main content
NVIDIA logo

Senior Software Engineer, NCCL

NVIDIA
September 19, 2026
Full-time
On-site
Santa Clara, California, United States
$152,000 - $287,500 USD yearly
EDA Jobs, Level - Senior

Job Title

Senior Software Engineer, NCCL

Role Summary

Senior software engineer on the GPU communications and networking team responsible for designing and implementing high-performance communication runtimes and system software for GPU clusters used in deep learning and HPC.

The role works on communication libraries (e.g., NCCL, UCX), parallel programming interfaces, and system-level software that enables GPU-to-GPU and GPU-to-system interactions.

Experience Level

Senior - 5+ years of relevant experience.

Responsibilities

Core responsibilities include design, implementation, and maintenance of communication runtimes and related system software; specification work and prototyping to drive runtime and hardware features.

  • Design, implement, and maintain optimized communication runtimes for deep learning frameworks (e.g., NCCL for PyTorch/TensorFlow) and HPC interfaces (e.g., UCX for MPI/OpenSHMEM).
  • Participate in and contribute to parallel programming interface specifications (MPI, OpenSHMEM).
  • Design and maintain system software enabling GPU-to-GPU and GPU-to-host interactions.
  • Create proofs-of-concept to evaluate programming model extensions, runtime designs, and hardware features.
  • Collaborate across teams in a multinational, multi-time-zone environment.

Requirements

Must-have technical skills and experience.

  • 5+ years of relevant software engineering experience (see Experience Level).
  • Excellent C/C++ programming and debugging skills.
  • Strong Linux experience.
  • Expert understanding of computer system architecture and operating systems.
  • Experience with parallel programming interfaces and communication runtimes.
  • Ability to communicate and work effectively across time zones and cultures.

Nice-to-have

  • CUDA programming experience and familiarity with NVIDIA GPUs.
  • Knowledge of high-performance networks (InfiniBand, iWARP, etc.).
  • Experience with HPC applications and deep learning frameworks (PyTorch, TensorFlow).
  • Proven collaborative and influencing skills in matrix environments.

Education Requirements

M.S. or Ph.D. in Computer Science, Computer Engineering, or a closely related technical field, or equivalent practical experience.


About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.

NVIDIA logo

Date Posted: 2026-09-17