Senior Software Engineer, Fabric Networking - GPU

Job Title

Senior Software Engineer, Fabric Networking - GPU

Role Summary

Join the GPU Fabric Networking team to design, deliver, and maintain system software that enables high-performance communication between GPUs for AI and HPC platforms. The role focuses on platform bring-up, feature enablement, end-to-end validation, and debugging for NVLink-based GPU and rack-scale systems.

Experience Level

Senior — typically requires 5+ years of professional software engineering experience.

Responsibilities

Primary responsibilities include development, validation, and troubleshooting of GPU networking and platform software.

• Design, implement, and maintain system software that enables efficient GPU-to-GPU communication.
• Participate in architecture and development of next-generation communication hardware and software for large-scale platforms.
• Drive platform bring-up, feature enablement, and end-to-end software validation and debugging for NVLink-based GPU and rack-scale systems.
• Triage and resolve complex issues across software, firmware, networking, and platform environments (validation, deployment, production).
• Improve software quality, performance, reliability, and scalability across the GPU networking stack.
• Collaborate with cross-functional engineering teams to translate technical requirements into working solutions.

Requirements

Must-have technical skills and experience; a short list of desirable skills follows.

• 5+ years professional software engineering experience (senior-level work with system software).
• Strong C/C++ programming, debugging, and problem-solving skills.
• Experience with shell scripting; familiarity with Python or Perl is a plus.
• Experience developing software that interfaces with device drivers and exposes hardware functionality.
• Solid understanding of computer architecture, operating systems, Linux kernel internals, and systems programming.
• Proven Linux development experience and ability to work across platforms including Windows.
• Experience developing multi-core, multi-process, and multi-threaded applications.
• Strong networking fundamentals: TCP/IP, Ethernet, InfiniBand, RDMA/RoCE, routing, switching, and fabric performance analysis.
• Familiarity with OS virtualization technologies such as KVM, QEMU, or Hyper-V.
• Excellent written and verbal communication skills for global, cross-functional collaboration.

Nice-to-have:

• Experience with NVIDIA GPU systems, NVLink, NVSwitch, CUDA, and large-scale AI/HPC clusters.
• Knowledge of PCIe, memory hierarchy, DMA, high-speed interconnects, and distributed training/inference architectures.
• Experience with server management, data center operations, cluster provisioning, scaling, and fleet monitoring.
• Familiarity with software QA techniques: static/dynamic analysis, fuzz testing, negative testing, and performance validation.
• Use of AI-assisted development tools and modern developer efficiency solutions.

Education Requirements

Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related technical field, or equivalent practical/comparable 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.