AI + HPC Hardware Performance ResearcherInitial 1 year freelance contract + possible extensionLeuven, Belgium (Hybrid – 3 days onsite per week)40 hours/weekASAP startThe assignmentYou will investigate software-hardware codesign innovations for next-gen artificial intelligence high performance computing systems.The Compute System Architecture Unit (CSA) at our client is researching next-generation large-scale heterogeneous computer architectures. The team is responsible for workload characterization, runtime management, performance modeling, architecture simulation and prototyping for future computer systems and their applications, to reach multiple orders of magnitude better performance, energy-efficiency, and total-cost-of-ownership.They are looking for an AI + HPC hardware performance researcher to innovate across layers of the computing stack, from application to semiconductor technology innovation and everything in between. You work closely with other experts from different fields to identify codesign solutions and to build the infrastructure required to evaluate them. This position plays a key role in their mission to shape the future of high performance computer architecture.You will:Research various solutions to enable the next large-scale-high-performance computing clusters. The role spans over various layers from workload characterization, resource management, system architecture, and microarchitecture.Develop performance (+power/TCO/emissions) models for future hardware at various levels of detail to identify bottlenecks and propose new solutions that alleviate the bottlenecks.Capture the relevant workload characteristics of the use of AI in HPC applications, as inputs to hardware models.Analyze performance on existing systems to validate and calibrate hardware models.Collaborate across the company to guide the direction of HPC HW/SW codesign based on the top HW issues and SW performance limiters generated from the models and characteristics.Model features and configurations that improve performance, power, total cost of ownership and emissions.Required knowledge and skillsMaster's or PhD degree in Computer Science, Computer Engineering or relevant STEM degree, preferably with early career experience.Experience with performance analysis of HPC applications, such as molecular dynamics or computational fluid dynamics. Experience with AI inside HPC applications is considered a plus.Experience with performance modeling (such as computer architecture simulation) for multiple types of computer hardware (e.G. CPU/GPU/NPU, or network design).Good understanding of heterogeneous system architectures, from their memory management to their microarchitecture.Good understanding of machine learning techniques, and their impact on performance.Strong programming ability in C++ and python. CUDA knowledge is considered a plus.Your communication and interpersonal skills enable you to work in a dynamic, distributed team. You actively share experiences and knowledge with colleagues.We are looking for your excellent communication skills in English, as you will work in a multicultural team and closely with our partners.