Senior Backend GPU Compiler Engineer

Job Description

The role You will be part of a diverse and distributed team of engineers who maintain and develop our GPU compiler software, supporting a range of graphics and compute APIs while targeting multiple GPU generations with varying ISAs. The GPU compiler is a central part of the drivers that we develop for these APIs. As such, they are critical to achieving optimal runtime performance of graphics/compute workloads on our GPUs, through the production of optimal HW code with minimal compilation time. You will: Maintain and develop our GPU compilers, with a focus on the LLVM based middle-end Diagnose and resolve incorrect compilation from customer issues, QA or conformance testing Analyse code-quality/runtime performance and implement optimisations Add support for new/future GPU functionality to the compilers Add support for new/future API/input language features Identify/suggest changes to improve output quality or compilation time Provide technical insight and collaborate with others to constantly improve our GPU compilers About You Committed to making your customers, stakeholders and colleagues successful, you?re an excellent communicator, listener and collaborator who builds trusted partnerships by delivering what you say, when you say. You?re curious, solutions orientated and a world-class problem solver who constantly seeks opportunities to innovate and achieve the best possible outcome to the highest imaginable standard. You'll have: Advanced C++ programming skills Strong knowledge of processes and techniques for compiler backend code-generation Experience with production-quality compiler development Strong compiler theory, especially optimisation Ability to analyse generated code down to the ISA level Computer architecture knowledge You might also have: Knowledge and experience with graphics/compute APIs such as OpenCL, cuda, Vulkan, OpenGL or DirectX Experience with compilation specifically for GPUs. LLVM backend development An appreciation of multi-threaded and/or parallel computation and associated complexity Knowledge of GPGPU programming Knowledge of AI/ML workloads that are amenable to GPU execution Who We Are Imagination is a UK-based company that creates silicon and software IP designed to give its customers an edge in competitive global technology markets. Its GPU and AI technologies enable outstanding power, performance, and area (PPA), fast time-to-market, and lower total cost of ownership. Products based on Imagination IP are used by billions of people across the globe in their smartphones, cars, homes, and workplaces. We need your skills to help us continue to deliver technology that will impress the industry and our customers alike, ensuring that people everywhere can enjoy smarter and faster tech than ever before. So come join us if you're wanting that something more Bring your talent, curiosity and expertise and we?ll help you do the rest. You?ll be part of one of the world?s most exciting companies who are one of the leaders in semiconductor IP solutions. As a part of our team, you can help us transform, innovate, and inspire the lives of millions through our technology. Additional Information If you encounter accessibility barriers in the application process or if you have access needs and require support or adjustments to participate equitably in the recruitment process, please email [email protected].