Skip to main content
Advanced Micro Devices logo

GPU Performance Architect

Advanced Micro Devices
September 11, 2026
Full-time
Remote friendly (Santa Clara, California, United States)
Worldwide
SoC Architecture Jobs, Level - Mid-Career

Job Title

GPU Performance Architect

Role Summary

Join AMD's Radeon Technologies Group (RTG) Architecture team to analyze graphics and compute workloads, identify bottlenecks, and propose performance, power, and area (PPA) improvements for GPUs and SoCs. The role focuses on workload/competitive analysis, simulation, and collaboration with architects and engineering teams across sites.

This position is based in Santa Clara, CA and is not eligible for visa sponsorship.

Experience Level

Mid-level (no explicit years of experience listed).

Responsibilities

Primary technical and collaborative duties:

  • Perform workload and competitive analysis of current and future game, AI, and ML applications.
  • Identify complex technical problems, decompose them, evaluate solutions, and guide implementation decisions.
  • Work with architects to locate and quantify bottlenecks in graphics cores and SoCs.
  • Analyze emerging graphics and compute paradigms and algorithms for architectural impact.
  • Implement and run simulation models (RTL and high-level) to estimate potential gains.
  • Propose innovative solutions to improve performance, power, and area (PPA).
  • Improve and drive development of RTG analysis and profiling tools.
  • Collaborate across distributed engineering and management teams.

Requirements

Core qualifications and desirable skills. Education items are listed separately below.

  • Self-motivated, collaborative team player with strong mentoring and communication skills.
  • Excellent analytical and problem-solving capability and attention to detail.
  • Experience with GPU architecture or performance analysis and identifying system bottlenecks.
  • Proficiency in C/C++ and scripting (Python) for analysis and tooling.
  • Familiarity with graphics/compute APIs and paradigms (DirectX, Vulkan, CUDA, HIP, etc.).
  • Experience implementing or running simulation models (RTL or high-level) is highly valued.
  • Nice-to-have: kernel development for LLMs (PyTorch, Triton, CUDA, HIP), experience with GFX profiling tools (PIX, RenderDoc, AMD tools), and compiler knowledge.

Education Requirements

Undergraduate degree required. Bachelor of Science preferred; Master’s or PhD in Electrical Engineering, Computer Architecture, Computer Science, or a closely related technical field is preferred.


About the Company

Company: Advanced Micro Devices

Headquarters: Sunnyvale, California, USA

Advanced Micro Devices, or AMD, is a global semiconductor company that designs and manufactures microprocessors, graphics processors, and related technologies for a variety of computing devices. Known for pushing the boundaries of innovation, AMD's mission is to deliver high-performance computing solutions for AI, data centers, gaming, and embedded applications. They foster a collaborative, inclusive culture focused on creativity and problem-solving, aiming to drive progress and excellence in technology.

Advanced Micro Devices logo

Date Posted: 2026-09-09