> Markdown version of [/jobs/ext/3536551-triton-compiler-and-kernel-software-engineer](https://www.wearedevelopers.com/jobs/ext/3536551-triton-compiler-and-kernel-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Triton Compiler and Kernel Software Engineer - **Company:** Advanced Micro Devices, Inc. - **Location:** San Jose, CA, United States - **Experience:** Expert - **Salary:** $204,000.0 - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Compilers, Code Generation, Profiling, Code Review, Nvidia CUDA, Computer Engineering, Software Debugging, Distributed Computing Environment, Python (Programming Language), Open Source Technology, Performance Tuning, Software Engineering, Graphics Processing Unit (GPU), Pytorch, Multi-Agent Systems, Distributed Programming, Parallel Computation, AI Coding Agents, Information Technology, Free and Open-Source Software, ROCm, MLIR (Multi-Level Intermediate Representation) - **Published:** October 1, 2026 - **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/18485454?backUrl=%2Fcareer%2F18485454%2FTriton-Compiler-Kernel-Software-Engineer-California-San-Jose ## About the Role 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., * Experience with AMD GPU architecture and ROCm is highly desirable. * Experience optimizing kernels with Triton, HIP, CUDA, or GPU assembly. * Experience with Triton, LLVM, MLIR, or another optimizing compiler. * Knowledge of GPU execution models, memory hierarchies, synchronization, and instruction pipelines. * Experience with collective communication, distributed programming, and libraries such as RCCL or NCCL. * Understanding of communication topologies, interconnects, synchronization, and communication-computation overlap. * Familiarity with distributed training, inference, tensor parallelism, expert parallelism, or pipeline parallelism. * Experience using AI coding tools and autonomous agents to accelerate software development, debugging, benchmarking, and kernel performance tuning. * Familiarity with AI primitives, reduced-precision formats, and performance profiling. * Contributions to complex or open-source software projects. * Strong analytical, debugging, communication, and collaboration skills., * Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent ## Description 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., * Develop and optimize Triton compiler support for AMD GPUs. * Improve compiler lowering, optimization, scheduling, and code generation. * Create high-performance kernels for attention, GEMM, MoE, and other AI workloads. * Develop and optimize multi-GPU kernels and communication primitives. * Enable new AMD GPU and interconnect capabilities through effective Triton abstractions. * Analyze compute, memory, communication, occupancy, register usage, and generated code. * Resolve complex correctness and performance issues across single- and multi-GPU workloads. * Collaborate with GPU architecture, ROCm, PyTorch, and AI framework teams. * Contribute designs and implementations to upstream Triton and LLVM/MLIR. * Provide technical leadership, code reviews, and mentoring., AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD's "Responsible AI Policy" is available here. ## Related Videos - [Photonic Computing: Programming a New Class of AI Accelerators (incl. Live Coding)](https://www.wearedevelopers.com/videos/100196-photonic-computing-programming-a-new-class-of-ai-accelerators-incl-live-coding) - [Coffee with Developers - Stephen Jones - NVIDIA](https://www.wearedevelopers.com/videos/1303-coffee-with-developers-stephen-jones-nvidia) - [Just-in-time Compilation in JVM](https://www.wearedevelopers.com/videos/240-just-in-time-compilation-in-jvm) - [Accelerating Python on GPUs](https://www.wearedevelopers.com/videos/859-accelerating-python-on-gpus) - [Building a Compiler with C#](https://www.wearedevelopers.com/videos/116-building-a-compiler-with-c) - [Serverless deployment of (large) NLP models ](https://www.wearedevelopers.com/videos/158-serverless-deployment-of-large-nlp-models) ## Related Articles - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Dev Digest 157: CUDA in Python, Gemini Code Assist and Back-dooring LLMs](https://www.wearedevelopers.com/magazine/557-dev-digest-157-cuda-in-python-gemini-code-assist-and-back-dooring-llms) - [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)