PhD in Physics-Informed Machine Learning for Semiconductor Metrology

This PhD position at ARCNL in Amsterdam focuses on advancing physics-informed machine learning to extract nanoscale information from noisy, low-resolution semiconductor metrology data. The project bridges computational science, mathematical modeling, and industrial applications, collaborating closely with ASML, CWI, and the University of Amsterdam’s AI4Science Lab. Applicants will design data-driven experimental setups and optimize measurement configurations for reliable parameter reconstruction. The role combines academic rigor with direct industry relevance, ideal for those passionate about interdisciplinary research at the intersection of AI and nanotechnology.

• Develop novel physics-informed machine learning models to reconstruct hidden nanoscale properties from imperfect measurement data.
• Integrate physical simulations of measurement processes with inverse reconstruction algorithms.
• Design and optimize data-driven experimental setups for semiconductor metrology applications.
• Collaborate with ASML’s research department to ensure industrial relevance and practical applicability.
• Conduct interdisciplinary research bridging computational science, mathematical modeling, and nanotechnology.
• Publish findings in high-impact academic journals and present results at international conferences.
• Participate in PhD courses and training programs offered by ARCNL and partner institutions.