Triton Compiler and Kernel Software Engineer

We are seeking a Senior Triton Compiler and Kernel Engineer to advance Triton performance and capabilities on AMD GPUs. Triton is an open-source language and compiler for developing high-performance GPU kernels in Python. It is a critical layer in the AI software stack, connecting frameworks and workloads to GPU hardware. Triton is strategic to AMD’s AI roadmap, and AMD is investing fully in making it a first-class platform for current and future AMD GPUs.

You will work across GPU architecture, compilers, kernels, multi-GPU communication, and AI frameworks while contributing to upstream Triton and AMD’s ROCm software stack. THE PERSON: The ideal candidate has strong experience in several of the following areas: GPU architecture and programming Compiler development and optimization High-performance GPU kernels Multi-GPU communication and collective operations Distributed AI training and inference AI workload and framework performance Low-level performance analysis You can reason across the stack—from distributed AI algorithms and Triton programs to compiler transformations, communication libraries, generated instructions, and GPU hardware.