Senior Systems Software Engineer - Data Center Performance
Core
Characterize node, rack, and cluster performance using microbenchmarks and representative applications to identify bottlenecks in compute, memory, communication, and storage for HPC and AI workloads.
Role type
Senior Systems Software Engineer (Data Center Performance)
Builds
High-performance datacenter platforms and clusters for HPC and AI
Domain
Data Center / High-Performance Computing (HPC) / AI Infrastructure
Deliverable
production ML models
Required skills
Linux performance analysis, Python, C/C++, CUDA, GPU application performance, NUMA, I/O, networking, profiling tools, distributed workload scaling
Preferred skills
Nsight Systems, Nsight Compute, Linux perf, eBPF, RDMA, MPI, NCCL, PCIe, NVLink, InfiniBand, Ethernet, Slurm, cgroups, ReFrame
Technologies
Python, C, C++, CUDA, Linux, Nsight Systems, Nsight Compute, Linux perf, eBPF, RDMA, MPI, NCCL, Slurm, ReFrame
Responsibilities
Characterize node, rack, and cluster performance using microbenchmarks and representative applications; Identify Linux performance problems related to CPU scheduling, NUMA locality, and resource contention; Examine distributed workload scaling and interconnect structure; Combine application profiles and system traces to isolate root causes; Develop and maintain Python tools for automated benchmark execution and analysis; Define and complete performance validation for new platforms and cluster deployments
Seniority
Senior, hands-on IC
