Senior GPU Compiler Development Engineer

Job description

WHAT YOU DO AT AMD CHANGES EVERYTHING At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond. Together, we advance your career. THE ROLE: AMD is looking for an MLIR compiler engineer who is passionate about representing and lowering deep-learning operators for next-generation large language and vision models on AMD GPUs. You will be a member of a core team of incredibly talented industry specialists and will work with the very latest hardware and software technology, building the MLIR dialect and operator-lowering surface — including a new single dynamic-shape graph. THE PERSON: The ideal candidate should be passionate about compilers and intermediate representations and possess the drive to take sophisticated issues to resolution. Able to communicate effectively and work optimally with different teams across AMD. KEY RESPONSIBILITIES: Help architect the dynamic-graph IR lowering on a single graph Implement operator definitions and MLIR lowerings for attention and control-flow operators required by new models Build model- and operator-level runtime-status reporting and analyze graph-optimizer behavior Contribute to MLIR dialect conventions and the operator-add checklist; review operator-lowering work Stay informed of compiler, algorithm, and architecture trends and apply them to the IR stack Debug and fix existing issues and research alternative, more efficient ways to accomplish the same work Develop technical relationships with peers and partners PREFERRED EXPERIENCE: Strong object-oriented programming background, C/C++ preferred, with a keen attention to detail Hands-on experience with MLIR (dialects, lowering, passes) Solid understanding of deep-learning operators and computational graphs LLVM, GPU programming (HIP / CUDA), and ONNX / ONNX Runtime experience is a plus Attention / transformer and diffusion operator internals; dynamic-shape and quantized inference is a plus Experience with Windows and Linux development; familiarity with debuggers, source code control systems (GitHub), and profilers Regular, hands-on use of AI coding agents / assistants to improve day-to-day engineering efficiency Professional working proficiency in English for cross-site collaboration Effective communication and problem-solving skills #LI-JW2 Benefits offered are described: AMD benefits at a glance . AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process. AMD may use Artificial Intelligence to help screen, assess or select applicants for this position. AMD’s “Responsible AI Policy” is available here. This posting is for an existing vacancy.