Host and Systems Performance Senior Manager
Core
Lead a team to measure, analyze, and improve NIC, host, DOCA networking stack, and system-level performance across NVIDIA networking products.
Role type
Senior management IC (systems performance engineering)
Builds
High-performance networking technologies (RDMA, RoCE, InfiniBand, Ethernet, MPI, NCCL, DOCA) for AI, HPC, and cloud workloads
Domain
Networking, HPC, AI infrastructure
Deliverable
production ML models
Required skills
Team leadership, performance analysis, systems engineering, high-performance networking (RDMA, RoCE, InfiniBand, Ethernet, MPI, NCCL), system performance benchmarking, root-cause analysis, host architecture (CPU, memory, NUMA, PCIe, Linux, drivers, firmware, DPU/NIC), test plan creation, Python/Bash scripting
Preferred skills
NIC/DPU architecture, networking offloads, host datapath behavior, AI/HPC cluster performance, distributed training, inference workloads, CUDA, NCCL internals, Linux kernel networking, DPDK, OVS, storage acceleration, security offloads, C/C++ programming
Technologies
RDMA, RoCE, InfiniBand, Ethernet, MPI, NCCL, DOCA, Linux, Python, Bash, C, C++, CUDA, DPDK, OVS
Responsibilities
Lead, coach, and develop a team focused on performance; define performance test plans, methodologies, metrics, and success criteria; guide pre-silicon and post-silicon performance planning, analysis, reporting, and readiness reviews; identify bottlenecks and lead root-cause analysis across NIC, DPU, CPU, memory, PCIe, firmware, drivers, and full-system architecture
Seniority
Senior, hands-on IC with management responsibilities
