AI Inference Software Engineer – GPU & Performance

Advanced Micro Devices, Inc.; Austin (TX); On-site; USD 140,000 - 190,000; Full time

Job summary

Advanced Micro Devices, Inc. is seeking a collaborative software engineer to develop and optimize AI inference software and runtimes for AMD platforms. You will identify bottlenecks, improve latency and throughput, and validate performance while building benchmarks and regression tests.

The role requires strong C/C++ and Python skills, experience with AI frameworks, and familiarity with GPU programming and related technologies. Location includes Austin, TX or Markham, Ontario, Canada.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.

Responsibilities

• Develop and optimize AI inference software and runtimes.
• Identify bottlenecks and improve latency, throughput, and memory efficiency.
• Integrate improvements and validate correctness and performance.
• Build benchmarks and automated regression tests.

Skills

C/C++

Python

AI frameworks

Perf profiling

GPU programming

PyTorch/ONNX/ROCm/HIP

Education

BSc or MSc in CS/CE/EE

Tools

PyTorch

ONNX Runtime

ROCm

HIP

Job description

Advanced Micro Devices, Inc. is seeking a collaborative software engineer to develop and optimize AI inference software and runtimes for AMD platforms. You will identify bottlenecks, improve latency and throughput, and validate performance while building benchmarks and regression tests.

The role requires strong C/C++ and Python skills, experience with AI frameworks, and familiarity with GPU programming and related technologies. Location includes Austin, TX or Markham, Ontario, Canada.