GPU Performance Architect for AI/Graphics Innovation

Advanced Micro Devices; Austin, Northern (TX, KY); Hybrid; USD 140,000 - 210,000; Full time

Job summary

Advanced Micro Devices in Austin, TX seeks a GPU Performance Architect to drive innovation in GPU hardware solutions and performance optimization. You will work with a global team to analyze workloads, identify bottlenecks, and iterate on RTL and high-level simulations to quantify gains.

The role requires strong C/C++ skills, graphics/compute knowledge, and collaboration across sites. A background in AI/ML workloads and GPU architectures is highly valued, with visa sponsorship not available.

Qualifications

• Experience spanning architecture, performance analysis and AI/ML/graphics/compute algorithms.
• Experience in Kernel development of LLMs using PyTorch, Triton, CUDA, HIP etc.
• Excellent C/C++/Scripting (Python, etc.) experience.

Responsibilities

• Work on workload/competitive analysis of contemporary and futuristic game/AI/ML applications.
• Identify complex technical problems, break them down, summarize solutions, and help progress.
• Analyze bottlenecks in graphics cores and SoCs with architects.
• Analyze existing and emerging graphics/compute paradigms and algorithms.
• Implement and run simulation models (RTL and high-level) to estimate gains.
• Propose innovative solutions for PPA improvements.
• Drive initiatives to improve RTG analysis tools.
• Collaborate with engineers and managers on multiple sites.

Skills

Graphics analysis

Performance analysis

C/C++

Python

Team collaboration

Presentation skills

Problem solving

Education

Bachelor's or Master’s in Electrical Engineering/Computer Science/Related

Tools

PIX

RenderDoc

AMD tooling

Job description

Advanced Micro Devices in Austin, TX seeks a GPU Performance Architect to drive innovation in GPU hardware solutions and performance optimization. You will work with a global team to analyze workloads, identify bottlenecks, and iterate on RTL and high-level simulations to quantify gains.

The role requires strong C/C++ skills, graphics/compute knowledge, and collaboration across sites. A background in AI/ML workloads and GPU architectures is highly valued, with visa sponsorship not available.