Join the Data and AI cluster at the Department of Mathematics and Computer Science, Eindhoven University of Technology, as a PhD candidate in scalable and safe AI for semiconductor metrology. This project aims to push multimodal generative AI beyond the lab, focusing on advanced model distillation and robustness methods to enable efficient and reliable inference for real-world challenges in the semiconductor industry. The research is motivated by the need for high-accuracy metrology in next-generation manufacturing processes, leveraging multimodal foundation models that combine data from multiple sources. As manufacturing matures, these models are specialized through efficient fine-tuning and distillation, improving throughput and maintaining performance guarantees on critical failure modes.

The PhD project centers on developing data-efficient methods for fine-tuning and distillation under strict data and privacy constraints, providing performance guarantees for specific downstream tasks. Customer data is often highly constrained, with limited and imbalanced datasets and strict privacy requirements. The project addresses evolving model performance requirements across the lifecycle of a process node, adapting to changing accuracy, speed, and defect-detection needs. The goal is to develop state-of-the-art techniques that facilitate robust metrology models and faster time-to-recipe across semiconductor process maturity stages.

Supervision is provided by Professor Mykola Pechenizkiy and Dr. Ghada Sokar at TU/e, in close collaboration with Dr. Jan Jitse Venselaar and Dr. Jacek Kustra from the ASML AI Research Team. The candidate will spend time at both TU/e and ASML locations, benefiting from access to national computing infrastructure, TU/e HPC cluster SPIKE-1, ASML HPC cluster, ASML datasets, and potential custom data through collaboration with IMEC. The project is part of the NWO TTW Perspectief funded research program 'Foundation for Industry (FIND)'—Large AI models for a resilient high-tech industry.

Applicants must have a master's degree in AI, Machine Learning, Data Science, Computer Science, or a closely related field, with a solid background in machine learning and strong programming skills. Enthusiasm for application-inspired ML research and interest in industrial collaboration are essential. Experience in model distillation, adaptation, and related topics is advantageous. Good academic writing and communication skills and fluency in English (C1 level) are required.

The position offers full-time employment for four years, with an intermediate assessment after nine months. Teaching tasks comprise a minimum of 10% of employment, with a maximum of 15% per year. Salary is in accordance with the Collective Labour Agreement for Dutch Universities, scale P (€3,059–€3,881/month), plus a year-end bonus (8.3%), annual vacation pay (8%), pension scheme, paid pregnancy and maternity leave, partially paid parental leave, commuting and home working allowances, and a 30% tax facility for international candidates. Additional benefits include high-quality training programs, excellent technical infrastructure, on-campus childcare, sports facilities, and support from the Staff Immigration Team.

To apply, submit your application online via the provided link. Include a cover letter, CV, MSc thesis or academic writing sample, and contact information for two references. Priority is given to complete applications. The vacancy remains open until filled, with a deadline of March 18, 2026. Applications sent by email or post will not be processed. For further information, contact Professor Mykola Pechenizkiy ([email protected]) or HR services M&CS ([email protected]).