Senior Software Engineer, AI (Triton Distributed Communication)

Quick Facts

• Role: Sr. Software Engineer focused on AI distributed execution using Triton on AMD GPUs

Description

Triton is a language and compiler for high-performance GPU kernels used by major AI frameworks. In this role, you will advance the Triton compiler and runtime stack for AMD CDNA and next-generation GPU architectures by building native distributed execution and communication capabilities. You will design and optimize mechanisms that enable efficient inter-GPU communication, scalable execution, and strong hardware utilization for large-scale AI workloads.

Responsibilities

• Design and develop native distributed communication and execution capabilities in the Triton AMDGPU backend for scalable multi-GPU AI workloads
• Implement Triton compiler and runtime mechanisms for native GPU-initiated communication, including collective operations, remote memory access, synchronization, and distributed execution primitives
• Drive performance optimization across compute and communication (inter-GPU data movement, communication/computation overlap, memory hierarchy utilization, and GPU-driven scheduling efficiency)
• Develop and optimize distributed Triton kernels and execution models for high performance, scalability, and efficient hardware utilization
• Analyze, profile, and debug cross-stack issues spanning Triton compiler, runtime, ROCm stack, and GPU hardware execution
• Collaborate with GPU architecture, compiler, runtime, and performance teams to co-design next-generation distributed GPU execution
• Contribute to the open-source Triton and ROCm distributed ecosystem

Requirements

• Deep expertise in GPU architecture, compiler technologies, and distributed GPU systems; proven experience optimizing workloads at multi-GPU scale
• Comfort working across the execution stack (compiler, runtime, and hardware) with strong understanding of GPU execution, memory hierarchy, and inter-GPU communication performance impacts
• Experience working close to the GPU runtime, communication stack, or compiler backend
• Motivated to build native distributed execution/communication capabilities tightly integrated with the compiler and runtime
• Ability to solve complex system-level performance challenges and deliver scalable, high-performance GPU infrastructure
• Bachelor’s or Master’s degree in a relevant field (or equivalent practical experience)

Benefits

AMD benefits at a glance.