MTS Software Development Engineer
Core
Architect and drive the AI Software Stack by establishing best practices and optimizing performance from lowest-level GPU kernels to large-scale distributed systems.
Role type
MTS Software Development Engineer (AI Stack & GPU Systems)
Builds
Foundational software for AMD hardware, specifically the ROCm ecosystem, supporting LLMs and autonomous AI agents.
Domain
Semiconductor / AI Infrastructure / High-Performance Computing
Deliverable
production ML models
Required skills
Modern C++, Object-Oriented Design, GPU programming (HIP or CUDA), Deep learning model architectures, Inference pipeline optimization, GPU architecture and memory hierarchy knowledge, GPU profiling and performance analysis.
Preferred skills
Experience with Large Language Models (LLMs) and agent-based technologies.
Responsibilities
Optimize performance from GPU kernels to distributed systems, accelerate development of LLMs and autonomous AI agents, contribute to the co-design lifecycle influencing future GPU architectures, develop software for new accelerators.
