AI Systems Engineer: High-Performance ML on Accelerators

AMD; San Jose (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

AMD is seeking an AI Systems Engineer in San Jose to develop and optimize ML workloads on next‑gen AMD accelerators. You will design high‑performance operator kernels, optimize dataflow, and enable AI inference across NPU and GPU platforms.

You will work across compiler, runtime, silicon, and architecture teams, guiding from kernel development to silicon bring‑up. Strong ML and architecture background is essential for impactful contributions.

Qualifications

• Master’s or PhD in Computer Engineering, Electrical Engineering, CS or related field preferred.
• Strong foundation in computer architecture and ML systems.
• Experience with GPUs/NPUs/AI accelerators and HPC platforms.

Responsibilities

• Develop and optimize ML operator kernels and dataflow libraries for AMD accelerators.
• Profile workloads, identify bottlenecks, and optimize software and system level performance.
• Enable and validate ML models within production inference frameworks and runtimes.

Skills

C/C++

Python

Parallel programming

ML frameworks

MLIR/LLVM

Quantization (INT8/FP8/FP16/BF16)

Computer architecture

GPU/AI accelerator programming

Linux development

Cross‑functional collaboration

Education

Master’s or PhD in a technical field

Tools

PyTorch

ONNX Runtime

ROCm

Job description

AMD is seeking an AI Systems Engineer in San Jose to develop and optimize ML workloads on next‑gen AMD accelerators. You will design high‑performance operator kernels, optimize dataflow, and enable AI inference across NPU and GPU platforms.

You will work across compiler, runtime, silicon, and architecture teams, guiding from kernel development to silicon bring‑up. Strong ML and architecture background is essential for impactful contributions.