GPU Performance Architect

Amd

Confirmed live today High trust
Hybrid

Quick summary

Work type
Hybrid
Location
Santa Clara, CA
Salary
$141,760–$212,640 / yr
Posted
48 days ago
Freshness
Confirmed live today
Closes
Sep 9, 2027

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $225k
This role $177k
$125k $294k
below market most similar roles pay here above market

This role pays less than 84% of similar roles. Most pay $196,137–$254,750 — the blue band above. At the midpoint, this role pays about $177k versus about $225k for comparable roles.

Based on 240 similar postings.

Employer

About Amd

AMD (Advanced Micro Devices) is a semiconductor company that develops high-performance processors, graphics cards, and adaptive computing solutions for gaming, data centers, and embedded markets. Industry: Semiconductors

Amd currently has 496 open roles on FindRole.

Listed pay typically runs $172,000–$258,000 across 496 roles with salary data.

Most-posted roles

View all roles at Amd

At a glance

TL;DR · GPU Performance Architect

The GPU Performance Architect joins the Radeon Technologies Group Architecture team to develop innovative hardware solutions and world-class GPUs. This role involves performing workload and competitive analysis on contemporary and futuristic game, AI, and ML applications to identify complex technical problems and propose PPA improvements. Daily responsibilities include analyzing graphics and compute paradigms, running RTL and high-level simulation models to estimate gains, and identifying bottlenecks in graphics cores and SoCs. The position requires expertise in C/C++, Python, and scripting, alongside knowledge of Graphics and Compute APIs like DirectX, Vulkan, CUDA, and HIP. Candidates should have experience with LLM kernel development using PyTorch and Triton, as well as familiarity with GPU architecture, compilers, and profiling tools like PIX or RenderDoc.

What you'll do

  • Perform workload and competitive analysis on contemporary and futuristic game, AI, and ML applications.
  • Identify complex technical problems and summarize multiple possible solutions to drive team progress.
  • Identify and analyze bottlenecks in graphics cores and SoCs with the architecture team.
  • Analyze existing and emerging graphics, compute paradigms, and algorithms.
  • Implement and run RTL and high-level simulation models to estimate potential performance gains.
  • Propose innovative solutions for Power, Performance, and Area (PPA) improvements.
  • Drive initiatives to improve Radeon Technologies Group analysis tools.

What we're looking for

  • An undergraduate degree is required.
  • A Bachelor of Science, Masters, or PhD degree with emphasis in Electrical Engineering, Computer Architecture, or Computer Science is preferred.
  • Experience spanning architecture, performance analysis, and AI/ML/graphics/compute algorithms is preferred.
  • Experience in Kernel development of LLMs using PyTorch, Triton, CUDA, or HIP is preferred.
  • Excellent C/C++ and scripting experience (such as Python) is preferred.
  • Knowledge of Graphics/Compute APIs (DirectX/Vulkan/CUDA/HIP etc.) is preferred.
  • Knowledge of GPU architecture and Compilers is preferred.
  • Experience in GFX profiling tools (PIX, RenderDoc, AMD tools, etc.) is a plus.

More like this

Similar roles

GPU Performance Architect

Amd

Austin, TX 53 days ago $178,400–$267,600
GPU Architecture CUDA HIP PyTorch Triton C++ C Python Vulkan DirectX High-Level Simulation Compilers AI/ML PIX RenderDoc Kernel Development

GPU System Performance Architect

Nvidia

Santa Clara, CA +2 43 days ago $224,000–$356,500
Computer Architecture Deep Learning High Performance Computing Performance Modeling Simulation Data Visualization Parallel Programming PCIe Cloud Computing AI Neural Networks Profiling
10+ yrs exp

GPU Benchmark Analysis Architect

Apple Inc

Cupertino, CA 40 days ago $216,200–$394,000
C++ Python Graphics APIs Computer Architecture Compiler Technologies Operating System Internals Firmware
10+ yrs exp