Senior Manager, Performance Engineering — Kernel and Software Platforms

Job Title

Senior Manager, Performance Engineering — Kernel and Software Platforms

Role Summary

Lead an engineering team that supervises and optimizes GPU software performance across the full hardware lifecycle: pre-silicon simulation/emulation, post-silicon bring-up, production hardware, and release support. Coordinate with compiler, architecture, and platform teams to set performance targets, maintain workload testlists, and align delivery with CUDA release cadence.

Promote automation of telemetry analysis and root-cause workflows using Python and generative AI tools to accelerate performance triage and reporting.

Experience Level

Senior-level. Requires 10+ years in systems/software performance engineering or platform benchmarking, and 5+ years leading or managing technical engineering teams.

Responsibilities

Own end-to-end performance engineering activities and ensure alignment of expectations, tooling, and delivery with software and hardware release schedules.

• Maintain continuous performance tracking from pre-silicon simulation/emulation through post-silicon validation and production hardware.
• Architect and maintain theoretical and empirical performance expectation models; correlate simulations with hardware telemetry to diagnose discrepancies.
• Analyze kernel authoring flows (DSL → IR → target code) to identify performance regressions and efficiency gaps.
• Create and maintain workload synthesis and stress-test suites to surface regressions early.
• Coordinate cross-functionally with compiler, architecture, and platform software teams to meet CUDA-linked release milestones.
• Integrate AI-driven automation (LLM APIs, agent workflows) to accelerate telemetry analysis, triage, and reporting pipelines.

Requirements

Must-have technical skills and experience to perform the role effectively.

• 10+ years in systems/software performance engineering, platform benchmarking, or equivalent.
• 5+ years of technical people management or leadership of engineering teams.
• Proven experience tracking performance across pre-silicon simulation, post-silicon bring-up, and production hardware.
• Experience building expectation models and correlating simulation predictions with hardware telemetry.
• Understanding of modern kernel compilation pipelines and how high-level abstractions affect low-level execution.
• Experience developing workload testlists and aligning performance efforts with major software release cycles.
• Proficiency in Python for automation and practical experience using generative AI APIs/models to automate triage and analysis workflows.

Nice-to-have:

• Experience building automated pre-to-post-silicon correlation pipelines for shift-left validation.
• Hands-on analytical experience with IRs such as MLIR, LLVM IR, NVVM/PTX.
• Experience designing agentic LLM workflows for automated regression analysis and root-cause summarization.

Education Requirements

MS or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent practical experience.

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.