Remote PMTS Systems Design Engineer for HPC & GPU AI

Socket.dev; Santa Clara (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Remote work option

AMD benefits at a glance

Travel: No

Job summary

AMD, Inc. is seeking a PMTS Systems Design Engineer to research, design, develop, and test operating systems for semiconductor operations, and to integrate software for GPU clusters supporting AI inferencing and training.

Remote work is possible; travel is not required. The role requires a Master’s degree and 5 years of related experience, with strong expertise in GPU performance, RDMA networking, and HPC system design.

Qualifications

• Master’s degree or foreign equivalent in Computer Science, Computer Engineering, Electrical Engineering, Telecommunications, or related field.
• Five (5) years of experience in the job offered or closely related engineering role.
• Alternate combination with Bachelor’s degree or foreign equivalent and seven (7) years of progressive post-baccalaureate experience.
• Position requires five (5) years of experience in GPU performance optimization, architectures, and HPC system design.

Responsibilities

• Research, design, develop, and test operating systems for semiconductor operations.
• Develop software systems and tools for design, infrastructure and technology platforms.
• Integrate software solutions enabling ethernet-based GPU-to-GPU communication for AI inferencing and training.
• Collaborate with hardware and software teams to enhance GPU cluster performance (RDMA, latency, throughput).
• Provide root cause analysis and lead debugging efforts to identify and resolve issues.
• Develop benchmarking strategies to assess baseline performance and identify bottlenecks in GPU clusters.

Skills

GPU performance optimization

GPU architectures & HPC

Parallel computing concepts

Python

Bash

System performance analysis

Debugging

Cluster management

RDMA networking

Linux kernel networking

Machine learning / HPC design

Education

Master’s degree in CS/CE/EE or related field

Bachelor’s degree + 7 years experience alternative

Tools

Linux

RDMA

Python

Job description

AMD, Inc. is seeking a PMTS Systems Design Engineer to research, design, develop, and test operating systems for semiconductor operations, and to integrate software for GPU clusters supporting AI inferencing and training.

Remote work is possible; travel is not required. The role requires a Master’s degree and 5 years of related experience, with strong expertise in GPU performance, RDMA networking, and HPC system design.