Job Summary:
NVIDIA is looking for an experienced Principal Software Engineer to expand the US-based Networking Hyperscale Engineering Team. In this role, you will co-develop software that powers AI superclusters and influence NVIDIA’s NIC software roadmap, working closely with top-tier cloud and AI customers.
Responsibilities:
• Co-developing NIC software and communication paths with strategic, top-tier customers to enable and scale large AI superclusters.
• Designing and implementing high‑performance C/C++ components on Linux using DPDK, kernel-bypass techniques, and RDMA/RoCE.
• Developing and integrating kernel, driver, and NIC firmware features to improve throughput, latency, and reliability for AI workloads.
• Working closely with NCCL and distributed training teams to tune end-to-end collectives performance over NVIDIA networking at scale.
• Owning complex performance and functionality debug with customers and representing the team in cross-org architecture discussions.
Qualifications:
Required:
• 15+ years overall experience in a similar or related systems / networking software role.
• A Bachelor’s, Master’s or PhD in Software Engineering, Computer Science, Computer Engineering, Electrical Engineering, or a related field (or equivalent experience).
• Deep C/C++ expertise, strong Linux systems knowledge, and hands-on experience with kernel networking / RDMA / NIC drivers or DPDK.
• Proven experience developing and debugging network operating systems (NOS) and routing/switching protocols used in AI data centers (for example BGP, ECMP, EVPN/VXLAN).
• Practical experience with DOCA, NIC firmware interfaces, or other hardware-accelerated networking stacks for large-scale systems.
• Excellent communication skills and a track record of effective collaboration with developers, partners, and customers in dynamic environments.
Preferred:
• Deep knowledge of Linux kernel / systems internals, SoC / SmartNIC / NIC embedded systems, and data center switches and NOS.
• Hands-on experience with RDMA/RoCE, GPU-related networking (for example GPUDirect RDMA), and high-performance, low-latency data paths.
• Background optimizing NCCL or other distributed training stacks on large GPU clusters for throughput and tail latency.
• Experience working with hyperscalers or major cloud providers on strategic, performance-critical AI networking deployments.
• Contributions to open-source networking, RDMA, DPDK, kernel, CUDA/NCCL, or related ecosystems.
Company:
NVIDIA is a computing platform company operating at the intersection of graphics, HPC, and AI. Founded in 1993, the company is headquartered in Santa Clara, USA, with a team of 10001+ employees. The company is currently Late Stage.