Staff GPU AI Software Engineer: Vision and ML Ops

AMD; Santa Clara (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Benefits at a glance

Job summary

AMD is seeking a Staff Software Developer to advance AI software on GPUs, focusing on high-performance C++ and low-level kernel work. You will shape the ROCm ecosystem, accelerate foundation models, and influence hardware-software co-design.

The role requires deep expertise in GPU programming, LLMs, and AI systems, plus capability to mentor others and drive technical strategy across teams.

Qualifications

• Extensive hands-on software development in performance-critical environments.
• Strong proficiency in modern C++ and GPU programming (HIP/CUDA).
• Deep knowledge of LLMs, transformer architectures, and AI systems.

Responsibilities

• Architect and drive the AI software stack from low-level kernels to distributed systems.
• Accelerate foundation models and AI agents, enabling AMD ROCm and AI workloads.
• Contribute to co-design across hardware and software, shaping future GPUs and accelerators.
• Mentor engineers, communicate technical direction, and own complex problems end-to-end.

Skills

Modern C++

HIP/CUDA

GPU programming

Kernel optimization

LLMs

AI systems

Distributed systems

Code generation

RLHF

Education

Bachelor’s or Master’s degree in CS/EE/CE

Tools

ROCm Profiler

NVIDIA Nsight

CUDA libraries

Job description

AMD is seeking a Staff Software Developer to advance AI software on GPUs, focusing on high-performance C++ and low-level kernel work. You will shape the ROCm ecosystem, accelerate foundation models, and influence hardware-software co-design.

The role requires deep expertise in GPU programming, LLMs, and AI systems, plus capability to mentor others and drive technical strategy across teams.