Staff GPU AI Software Architect: Vision & ML Ops

Advanced Micro Devices; Santa Clara (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Advanced Micro Devices seeks a Staff Software Developer to advance AI software on AMD GPUs, spanning low-level kernel work to large-scale distributed systems. You will shape the ROCm ecosystem and drive performance improvements across AI workloads.

The role emphasizes deep C++/HIP/CUDA proficiency, experience with LLMs, and leadership in cross-team collaboration. A strong foundation in AI systems and kernel optimization is essential for this high-impact position.

Qualifications

• Senior role requiring blend of software, GPU computing, and AI expertise.
• Extensive GPU programming experience and optimizing deep learning kernels.
• Strong C++ and object-oriented design skills.
• Experience or expertise with ROCm/HIP is a plus.
• Familiarity with LLMs and AI systems, transformer architectures.

Responsibilities

• Architect and drive the AI software stack from low-level GPU kernels to large-scale distributed systems.
• Accelerate foundational models and autonomous AI agents.
• Contribute to the co-design lifecycle of hardware and software for AMD GPUs.
• Mentor other engineers and communicate technical direction across teams.
• Bridge kernel engineering with AI post-training (RL) experience.

Skills

C++ expertise

HIP/CUDA programming

GPU kernel optimization

AI systems knowledge

Kernel engineering

Multi-GPU systems

Transformer architectures

Performance profiling

Education

Bachelors or Masters in CS/EE/CE

AI/ML publications

Tools

ROCm

NVIDIA Nsight

CUDA libraries

PyTorch

TensorFlow

Job description

Advanced Micro Devices seeks a Staff Software Developer to advance AI software on AMD GPUs, spanning low-level kernel work to large-scale distributed systems. You will shape the ROCm ecosystem and drive performance improvements across AI workloads.

The role emphasizes deep C++/HIP/CUDA proficiency, experience with LLMs, and leadership in cross-team collaboration. A strong foundation in AI systems and kernel optimization is essential for this high-impact position.