Tristan van Leeuwen

This PhD project addresses a core challenge in semiconductor metrology: recovering nanoscale physical information from limited, noisy, and low-resolution images. The work focuses on developing a physics-informed machine learning approach that combines physical simulation of the measurement process with inverse reconstruction methods, aiming to infer hidden properties of modern chip structures efficiently and reliably. The project is situated at ARCNL, an institute dedicated to fundamental research on the physics and chemistry behind current and future nanolithography technologies for the semiconductor industry. ARCNL works in close connection with ASML, giving the project strong industrial relevance while maintaining a research environment focused on scientific excellence. The institute is based at Amsterdam Science Park and hosts an international community of researchers. You will collaborate closely with researchers at ASML, the Centrum Wiskunde & Informatica, and the AI4Science Lab at the Informatics Institute of the University of Amsterdam. The topic combines computational science, mathematical modeling, and data-driven methods, with a particular emphasis on how measurement choices and experimental configurations can be optimized to improve parameter reconstruction. This makes the position especially relevant for students interested in the interface between machine learning, physical modeling, and advanced measurement science. The appointment is hosted by ARCNL and leads to a PhD degree at a Dutch university upon successful completion. The institute also offers a structured environment with courses designed for PhD students and support for international researchers.