Get a reply from this employer
Your resume and cover letter, tailored to exactly what they’re hiring for.
AMD is advancing Triton-based distributed AI for AMD Instinct GPUs, building native distributed execution and communication within the Triton AMDGPU backend. You will optimize inter-GPU data movement, synchronization, and overlap of compute with communication across multi-GPU systems.
The role spans compiler, runtime, and hardware layers, collaborating with architecture and performance teams to deliver scalable GPU infrastructure and contribute to open-source Triton/ROCm projects.
AMD is advancing Triton-based distributed AI for AMD Instinct GPUs, building native distributed execution and communication within the Triton AMDGPU backend. You will optimize inter-GPU data movement, synchronization, and overlap of compute with communication across multi-GPU systems.
The role spans compiler, runtime, and hardware layers, collaborating with architecture and performance teams to deliver scalable GPU infrastructure and contribute to open-source Triton/ROCm projects.