Senior Manager, Performance Engineering - Kernel and Software Platforms

What you'll do

• Supervise and maintain performance tracking for GPU products across the entire lifecycle from pre-silicon simulation to production hardware.
• Architect theoretical and empirical performance models to set targets and correlate simulation predictions with physical hardware telemetry.
• Evaluate and benchmark performance translation across kernel authoring flows from high-level DSLs through compiler intermediate representations.
• Create and maintain stress-test suites and workload testlists to detect regressions and validate hardware release candidates.
• Coordinate with cross-functional teams to align performance achievements with the official CUDA release schedule.
• Integrate AI tools and LLM workflows to automate telemetry analysis, root-cause identification, and reporting pipelines.

What we're looking for

• MS or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent experience.
• Experience in systems/software performance engineering, platform benchmarking, or a related area.
• 5+ years of experience leading or managing technical engineering teams.
• Demonstrated track record tracking performance through the entire hardware pipeline from design-time simulation to post-silicon production.
• Proven ability to build expectation models and correlate simulation predictions with physical hardware telemetry.
• Understanding of modern kernel compilation pipelines, compiler flows (DSL to IR), and how high-level software impacts execution efficiency.
• Experience developing workload testlists to detect regressions and aligning performance delivery with major software release cycles.
• Proficiency in Python automation and experience using generative AI models to automate triage and analytical workflows.