Senior Software Engineer, NCCL and CUDA - CSP Engagements

The NVIDIA Cloud Service Provider (CSP) Engagements team is looking for a Senior Software Engineer specializing in NCCL and CUDA to enhance the ML software stack’s functionality and performance for datacenter products such as GB300 and Vera Rubin. This role involves collaborating with customers to diagnose and resolve functional and performance issues in the libraries layer for large-scale deployments, while leveraging deep expertise in workloads, NCCL and CUDA libraries, frameworks, and system software interactions to drive innovation. What You Will Be Doing Engage with CSPs to root cause functional and performance problems in NCCL and CUDA libraries. Analyze and improve multi‑GPU workload performance through profiling, benchmarking, and tuning. Resolve NCCL and NVSHMEM data‑movement issues in multi-node clusters. Address CUDA porting challenges for customer workloads. Apply datacenter‑specific scheduling and topologies for optimal performance. Debug and resolve complex GPU computation, memory, and transport issues. Collaborate with customers to understand workload integration challenges and propose tailored solutions aligned with the NVIDIA ecosystem. Work with AE, FAE, and solution architects to deliver integrated customer solutions and technical documentation. Assist customers in adopting the latest CUDA and NCCL advancements. What We Need To See Experience with parallel programming models and communication libraries (MPI, NCCL, NVSHMEM) runtime. Experience with performance‑optimization and profiling tools such as Nsight and nvprof. Strong C/C++ programming and debugging skills, with CUDA development experience. Exposure to PCIe and NVLINK. Deep understanding of operating systems and data‑center system architecture. Knowledge of high‑performance networking like InfiniBand and RoCE. Proficient understanding of compute, networking, and cloud deployment on bare‑metal and VMs. BS or MS in Computer Engineering, Computer Science, or related field (or equivalent experience). Familiarity with containers, cloud provisioning and scheduling tools such as Docker, Kubernetes, SLURM, and Ansible. 8+ years of system‑software validation experience. Strong communication and collaboration skills with partner and customer teams. Ways To Stand Out From The Crowd Strong software‑architecture experience. Experience with deep‑learning workloads for training and inference. Experience conducting performance benchmarking and developing tooling on HPC clusters. Base salary ranges from USD 184,000 to 287,500 for Level 4, and USD 224,000 to 356,500 for Level 5, depending on location and experience. You will also be eligible for equity and benefits. Applications are accepted until June 23, 2026. We are an equal‑opportunity employer committed to fostering an inclusive work environment and do not discriminate on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status, or any other protected characteristic. #J-18808-Ljbffr NVIDIA