Senior AI Cluster Performance Validation Engineer

Advanced Micro Devices

Austin, Northern (TX, KY)

Hybrid

USD 180,000 - 230,000

Full time

4 days ago

Be an early applicant

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Job summary

Advanced Micro Devices (AMD) in Austin is seeking a Principal AI Cluster Performance Validation Engineer to optimize GPU clusters and RDMA networks. You will lead performance tuning, profiling, and validation across multi-node systems, collaborating with HW and SW teams.

The role requires strong background in GPU architectures, parallel computing, and hands-on system-level debugging. You’ll shape long-term strategy, drive feature enablement, and stay ahead of industry trends to improve cluster

Qualifications

Bachelor's or Master's in CS or EE.
Experience optimizing GPU cluster performance.
Strong knowledge of RDMA, RoCE, and clustering.
Proficiency in Python or Bash for automation.

Responsibilities

Scalability testing of GPU clusters under varying workloads and RoCE.
Benchmarking and analysis to identify bottlenecks and opportunities for improvement.
Cluster network and performance optimization focusing on RDMA throughput, latency, and collective communications.
Performance profiling and tuning using established tools and methodologies.
Documentation of performance analyses, tuning efforts, and outcomes; reporting to stakeholders.