Senior AI GPU Cluster Performance Engineer

Advanced Micro Devices; Austin (TX); On-site; USD 100,000 - 130,000; Full time

Job summary

Advanced Micro Devices in Austin, TX, is seeking a GPU Cluster Network Performance Attainment Engineer. This role focuses on optimizing GPU cluster performance with a strong emphasis on RDMA networks.

The ideal candidate will have extensive experience in GPU architectures and parallel computing, with proficiency in performance tuning and debugging. The position offers a collaborative environment with opportunities for continuous learning and impact on innovative technology.

Qualifications

• Proven experience in optimizing GPU cluster performance.
• Understanding of RDMA network drivers.
• Strong understanding of network protocols.

Responsibilities

• Evaluate the scalability of GPU clusters under various workloads.
• Utilize profiling tools to analyze performance bottlenecks.
• Implement optimization strategies for performance tuning.

Skills

GPU architectures

Parallel computing

Performance tuning

Scripting languages (Python, Bash)

Debugging complex HW/FW and drivers

Collaboration with cross-functional teams

Education

Bachelors or Masters degree in electrical or computer engineering

Tools

Performance analysis tools

Cluster management tools

Job description

Advanced Micro Devices in Austin, TX, is seeking a GPU Cluster Network Performance Attainment Engineer. This role focuses on optimizing GPU cluster performance with a strong emphasis on RDMA networks.

The ideal candidate will have extensive experience in GPU architectures and parallel computing, with proficiency in performance tuning and debugging. The position offers a collaborative environment with opportunities for continuous learning and impact on innovative technology.