Senior Systems Software Engineer - Data Center Performance

Details

NVIDIA is hiring an engineer for its Applied Systems Engineering Performance team. The role combines experimentation and software engineering to evaluate emerging platforms under demanding HPC and AI workloads, identify performance limitations, establish reliable measurements, and help improve platform performance at datacenter scale.

Responsibilities

• Characterize node, rack, and cluster performance using microbenchmarks and representative applications.
• Measure throughput, latency, and scaling efficiency to identify compute, memory, communication, and storage bottlenecks.
• Investigate Linux performance issues involving CPU scheduling, NUMA locality, CPU and memory affinity, interrupt handling, and resource contention.
• Analyze distributed workload scaling, including collective communication, synchronization delays, slow nodes, computation and communication interaction, GPU and NIC positioning, interconnect structure, and network traffic.
• Combine application profiles, system traces, hardware counters, and cluster telemetry to identify root causes.
• Develop focused reproductions and collaborate with hardware, firmware, driver, library, and application teams to implement and verify fixes.
• Develop and maintain Python tools for automated benchmark execution, data collection, and performance analysis.
• Establish repeatable baselines, assess run-to-run variability, and identify regressions across hardware configurations and software releases.
• Define and complete performance validation for new platforms and cluster deployments.
• Identify underperforming nodes, links, or storage paths and verify corrective actions.

Requirements

• Extensive practical experience with Linux performance analysis, including processes and threads, CPU and memory architecture, NUMA, I/O, and networking.
• Experience investigating performance in multi-node HPC or GPU-accelerated systems.
• Ability to distinguish local resource bottlenecks from communication overhead, load imbalance, and shared-resource contention.
• Deep expertise in at least one of the following: GPU application performance, Linux systems performance, high-speed networking and collective communication, parallel storage, or HPC performance tooling.
• Proficiency in Python for building maintainable automation and analysis tools.
• Experience developing and debugging performance-sensitive code in C, C++, and CUDA.
• Ability to build controlled experiments, interpret profiling and counter data, and demonstrate reproducible application performance improvements.
• Ability to independently drive technical efforts across hardware and software boundaries, communicate findings clearly, and work with component owners to resolve issues.
• Bachelor’s or master’s degree in Computer Science, Engineering, Mathematics, Physics, or equivalent experience.
• 8+ years of applicable experience.

Preferred Qualifications

• Experience with Nsight Systems, Nsight Compute, Linux perf, or eBPF-based profiling and tracing tools.
• Practical experience with RDMA and MPI or NCCL.
• Experience analyzing performance across PCIe, NVLink, InfiniBand, or Ethernet interconnects.
• Experience with Slurm, container runtimes, and cgroups.
• Understanding of workload placement, resource isolation, and CPU, GPU, and NIC affinity.
• Experience improving distributed training, inference, or scientific applications through strong- and weak-scaling studies.
• Experience building automated performance regression frameworks using tools such as ReFrame.

Compensation

The expected annual base salary ranges are:

• Poland: PLN 292,500–507,000 for Level 4 and PLN 375,000–650,000 for Level 5.
• France: EUR 87,750–152,100 for Level 4 and EUR 114,000–197,600 for Level 5.
• Germany: EUR 112,200–194,480 for Level 4 and EUR 141,900–245,960 for Level 5.

Base salary depends on location, experience, and other objective job-related factors.