System Software Engineer - Performance

NVIDIA NVIDIA · Semiconductors · Santa Clara, CA +5 · Remote

System Software Engineer focused on performance optimization for NVIDIA's next-generation SoCs, including CPUs and CPU+GPU Superchips, within the Tegra system-on-chip (SoC) software organization. The role involves designing, developing, testing, and optimizing software for pre-silicon and post-silicon phases, analyzing performance bottlenecks, and developing tools for performance analysis.

What you'd actually do

  1. Design, develop, test, and optimize software for our next-generation SoCs, in both pre-silicon and post-silicon phases of execution.
  2. Analyze and identify performance bottlenecks in the SOC.
  3. Using strong communication skills, analysis documents and communications to internal and/or external audiences about our technology.
  4. Competitive analysis comparing uArchitecture & workload performance metrics on NVIDIA's ARM SoCs against emerging processors from other silicon vendors.
  5. Develop tools and use benchmarks to analyze performance

Skills

Required

  • BS or MS degree in Computer Engineering, Computer Science, or related degree (or equivalent experience).
  • 2+ years of relevant computer architecture or SW development experience.
  • Hands on technical experience and demonstrated excellence in an environment with complex software and hardware designs.
  • Strong understanding of multicore hardware, operating systems design, concurrency, virtual memory, caching, interrupts, device drivers and real-time programming.
  • Experience in performance analysis, data analysis and performance optimization.

Nice to have

  • Expertise in ARM architecture and SW ecosystem.
  • Proficient in analyzing, debugging and tuning performance of complex system software stacks.
  • Experience with CPU server system workloads and performance analysis.
  • Familiarity with CUDA programming and/or GPUs.
  • Experience with HPC or large-scale computing environments.

What the JD emphasized

  • performance analysis
  • performance optimization
  • performance bottlenecks