GPU Performance Architect

AMD
United States
Workplace: HybridFull timeUSD 106,470 - 182,520 annuallyFunction: Hardware, Embedded & Systems EngineeringEducation: bachelorsSkills: ["Analytical","Problem-solving","Communication","Time management","Presentation"]

Drive GPU and SoC performance improvements for next-generation game and AI/ML workloads by analyzing contemporary and emerging graphics/compute paradigms. Identify bottlenecks across graphics cores, run RTL and high-level simulations, and propose PPA optimization ideas. Collaborate with architects, engineers, and managers across multiple sites while improving RTG analysis tools to deliver measurable performance gains.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
AMD
AMD
2 days ago

GPU Performance Architect

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 21 hours agoStatus: Live

Job Summary

Drive GPU and SoC performance improvements for next-generation game and AI/ML workloads by analyzing contemporary and emerging graphics/compute paradigms. Identify bottlenecks across graphics cores, run RTL and high-level simulations, and propose PPA optimization ideas. Collaborate with architects, engineers, and managers across multiple sites while improving RTG analysis tools to deliver measurable performance gains.
Location: United States
Workplace: Hybrid
Employment Type: Full time
Job Function: Hardware, Embedded & Systems Engineering
Seniority: Mid level

Key Responsibilities

  • •Perform workload and competitive analysis for contemporary and futuristic game/AI/ML applications.
  • •Identify complex technical problems, decompose them, propose solution approaches, and help the team progress.
  • •Work with architects to understand bottlenecks in graphics cores and SoCs.
  • •Analyze existing and emerging graphics/compute paradigms, algorithms, and simulation models (RTL and high-level).
  • •Propose PPA improvement solutions and help drive initiatives to improve RTG analysis tools while collaborating across multiple sites.

Pay and Benefits

Salary: USD 106,470 - 182,520 annually

Key Requirements

  • •Undergrad degree required (Electrical Engineering, Computer architecture, or Computer Science preferred).
  • •Experience spanning architecture and performance analysis for AI/ML, graphics, and compute workloads.
  • •Experience developing kernels for LLMs using PyTorch, Triton, CUDA, and HIP.
  • •Excellent C/C++ and scripting (Python, etc.) experience.
  • •Knowledge of graphics/compute APIs (DirectX, Vulkan, CUDA, HIP) and GPU architecture and compilers.
Experience:AI/MLGraphicsCompute
Education:Bachelor's in Electrical Engineering, Computer architecture, or Computer Science
Skills:AnalyticalProblem-solvingCommunicationTime managementPresentation
Languages:English
Tech Stack:PythonCC++PyTorchTritonCUDAHIPDirectXVulkanPIXRenderDoc

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

AMD
Designs and produces semiconductor products including CPUs, GPUs, and adaptive SoCs for consumer, enterprise, and embedded markets, competing across PCs, data centers, and gaming industries.
Industry: Electronics Manufacturing
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Santa Clara, United States
Founded: 1969
Glassdoor
Glassdoor: 3.9
WebsiteLinkedIn