AI/ML Compiler Engineer, High-Performance GPUs

Advanced Micro Devices; San Jose (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Advanced Micro Devices in San Jose, CA is seeking a highly motivated PMTS AI/ML Compiler Engineer to drive compiler and performance optimizations for AI training and inference on AMD GPU platforms. You will work at the intersection of compiler tech, ML frameworks, GPU architecture, and performance engineering within the ROCm and ONNX Runtime stacks.

The ideal candidate combines deep compiler expertise with hands-on AI workload optimization, collaborates with architecture, kernel, runtime, and

Qualifications

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
• Strong compiler fundamentals and GPU programming experience.
• Experience optimizing AI workloads across ML frameworks.

Responsibilities

• Design, develop, and optimize compiler transformations and operator lowerings within MLIR, LLVM, and the ROCm software stack.
• Develop scalable solutions to improve portability and performance across AMD GPU architectures.
• Collaborate with compiler and runtime teams to optimize AI workloads and implement ONNX operators.
• Lead performance optimization efforts for AI training and inference on AMD GPUs.

Skills

C++

GPU programming

MLIR/LLVM

AI workload optimization

Profiling & optimization

Linux & Git

Performance tooling

Education

Bachelor’s or Master’s degree in Computer Science/Engineering

Tools

HIP

CUDA

Triton

ONNX

ROCm

MLIR

LLVM

Job description

Advanced Micro Devices in San Jose, CA is seeking a highly motivated PMTS AI/ML Compiler Engineer to drive compiler and performance optimizations for AI training and inference on AMD GPU platforms. You will work at the intersection of compiler tech, ML frameworks, GPU architecture, and performance engineering within the ROCm and ONNX Runtime stacks.

The ideal candidate combines deep compiler expertise with hands-on AI workload optimization, collaborates with architecture, kernel, runtime, and