Principal AI & High-Performance Computing Architect

Shape the architecture behind the next generation of AI supercomputers.

Join imec and design the future of AI computing

What if your architectural decisions could influence the future of artificial intelligence at the scale of the world's most advanced computing systems?
At imec, you will work at the intersection of AI, semiconductor innovation, and large-scale computing architectures. Together with leading experts in computing systems, chip technology, software, and artificial intelligence, you will help define how future AI infrastructure is built, optimized, and scaled.
This is not a product maintenance role. It is an opportunity to explore breakthrough architectures that could shape the next decade of AI and high-performance computing.

What you will do

As a Principal AI & High-Performance Computing Architect, you will drive innovation across the entire computing stack, from AI applications and system software to processors, accelerators, and semiconductor technologies.
You will create models, simulations, and design explorations that help identify the most promising paths toward future AI computing systems that deliver significant improvements in performance, energy efficiency, and sustainability.

Your responsibilities include:

• Exploring architectural solutions for next-generation AI and high-performance computing clusters.
• Analysing the behaviour and performance characteristics of large-scale AI workloads.
• Developing performance models that identify bottlenecks and opportunities for innovation.
• Evaluating future processor, accelerator, memory, and system designs.
• Collaborating with experts in computer architecture, AI, semiconductor technology, system software, and modelling.
• Defining requirements for future AI computing platforms and processor architectures.
• Guiding strategic research directions through data-driven performance analysis and projections.
• Contributing to breakthrough innovations that improve performance, energy efficiency, operational cost, and environmental impact.

Who you are

• Master’s or PhD degree in Computer Science, Computer Engineering or relevant STEM degree, with at least around 8 years of experience. 
• Experience with performance analysis, engineering, and optimization of HPC applications, such as molecular dynamics and computational fluid dynamics,
• Experience in AI for HPC is a plus. 
• Experience with distributed AI/ML applications, such as LLM training and inference. 
• Experience in system performance modeling ranging from a single device (e.g. a GPU) to a machine scale (e.g. a cluster).
• Good understanding of GPU (preferably XPU) system architectures, distributed programming models, runtime resource management, and microarchitecture. 
• 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. A history of mentoring more junior engineers and interns is a huge plus. 
• We are looking for your excellent communication skills in English, as you will work in a multicultural team and together with our partners.