About The Position

The Graphics, Games and Machine Learning organization is looking for a talented Performance Engineer to help drive our validation and performance analysis efforts on new SoCs. As a member of the GPU Driver Performance Team, you will be responsible for the end-to-end performance validation of our GPU hardware and software platforms. This process starts with ensuring that we have proper workload representation in our presilicon environments to evaluate performance on emerging GPU architectures, and continues with validating that performance on silicon ultimately aligns with expectations. You will help to build the tools and infrastructure that we use for validating GPU performance at scale, and learn how our GPUs work and perform at a foundational level. You will also collaborate closely with architecture, hardware design, and driver engineers to debug complex issues and drive solutions. Your deep-dive analysis and rigorous testing will identify performance bottlenecks, regressions, and opportunities for optimization across the software stack, as well as help inform our future hardware roadmap.

Requirements

  • Bachelor's or Master's degree in Computer Science, Computer Engineering, or a related technical field.
  • Experience in performance analysis, hardware validation, or a similar role.
  • Strong understanding of computer system architecture, with an emphasis on GPU architecture.
  • Proficiency in a scripting language such as Python (preferred), Perl, or Bash.
  • Excellent problem-solving and debugging skills.
  • A passion for GPU performance, graphics technologies, and high-performance computing.

Nice To Haves

  • Hands-on experience with GPU performance profiling and debugging tools (e.g., Nsight, RGP, GPA, RenderDoc).
  • Familiarity with modern graphics APIs (e.g., Metal, Vulkan, DirectX 12).
  • Experience with containerization and orchestration technologies (e.g., Docker, Kubernetes) or other cloud-based solutions for test infrastructure.
  • Knowledge of system-level power and thermal management and its impact on performance.

Responsibilities

  • Drive validation and performance analysis efforts on new SoCs.
  • Ensure proper workload representation in presilicon environments.
  • Validate performance on silicon to align with expectations.
  • Build tools and infrastructure for validating GPU performance at scale.
  • Collaborate with architecture, hardware design, and driver engineers.
  • Debug complex issues and drive solutions.
  • Identify performance bottlenecks, regressions, and optimization opportunities.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service