Principal Software Engineer, E2E Performance and Goodput — CSP Engagements

Job Description

Lead end-to-end performance characterization and validation with CSP and hyperscale customers, including profiling workloads, analyzing performance gaps, and ensuring benchmarks and tooling are ready for deployment. Synthesize cross-customer findings and drive optimization priorities, documentation, configuration guidance, and systemic improvements across NVIDIA engineering teams.

Requirements: Requires 15 or more years of systems performance engineering experience, ideally in GPU, HPC, or ML infrastructure, and a bachelor's or master's degree in a related field or equivalent experience. Candidates should have GPU profiling and distributed-training expertise, statistical performance-analysis and data skills, knowledge of the software stack, and the ability to influence engineering teams and communicate with technical and executive audiences.

Key Skills: Systems Performance Engineering, GPU Workload Profiling, Distributed Training Performance, Performance Characterization, Statistical Performance Analysis, Python, Pandas, Data Visualization, CUDA, NCCL, Performance Regression Detection, Benchmarking, Customer Engagement, Cross-Functional Influence, Inference Performance

Benefits: Equity, Benefits