Key Skills

Job Description

Work Activities How can we combine machine learning and physics to recover nanoscale information from imperfect images? Modern computer chips are built with features only a few nanometers across, yet manufacturers need to measure these structures with extraordinary precision and do so quickly enough to keep up with large-scale production. This creates a fascinating computational challenge: how can we infer hidden physical properties from limited, noisy, and low-resolution measurement data? In this project, you will develop a novel physics-informed machine learning approach that integrates physical simulations of the measurement process with its inverse reconstruction. A key challenge is the data-driven design of the experimental setup: exploring how the choice of measurements and configurations can be optimized to extract the most useful information for reliable parameter reconstruction. You will work in close collaboration with the research department at ASML, the Centrum Wiskunde & Informatica (CWI, Prof. dr. Tristan van Leeuwen), and the AI4Science Lab, Informatics Institute, University of Amsterdam (dr. Patrick Forré), combining industrial relevance with academic depth in computational science and mathematical modeling. Qualifications You have (or soon will have) a MSc degree in computer science, machine learning, artificial intelligence, applied mathematics, physics, or a related discipline, meeting the Dutch university requirements for entry into a PhD program. A background in machine learning, inverse problems, scientific computing, or related data-driven methods is highly desirable. You are curious about combining physical modeling with data-driven methods and are motivated to work at the interface of academia and industry. Strong analytical skills, a collaborative mindset, and proficiency in verbal and written English are essential. Work environment ARCNL performs fundamental research, focusing on the physics and chemistry involved in current and future key technologies in nanolithography, primarily for the semiconductor industry. While the academic setting and research style are geared towards establishing scientific excellence, the topics in ARCNL’s research program are intimately connected with the interests of the industrial partner ASML. The institute is located at Amsterdam Science Park and currently employs about 100 persons of which 65 are ambitious (young) researchers from all over the globe. www.arcnl.nl Working conditions The position is intended as full-time (40 hours / week, 12 months / year) appointment in the service of the Netherlands Foundation of Scientific Research Institutes (NWO-I) for the duration of four years, with a starting salary of gross € 3.115 per month and a range of employment benefits. After successful completion of the PhD research a PhD degree will be granted at a Dutch University. Several courses are offered, specially developed for PhD-students. ARCNL assists any new foreign PhD-student with housing and visa applications and compensates their transport costs and furnishing expenses. More information? For further information about the position, please contact Lyuba Amitonova: [email protected] and Maximilian Lipp ([email protected]). Application You can respond to this vacancy online via the button below. Online screening may be part of the selection. Diversity code ARCNL is highly committed to an inclusive and diverse work environment: we want to develop talent and creativity by bringing together people from different backgrounds and cultures. We recruit and select on the basis of competencies and talents. We strongly encourage anyone with the right qualifications to apply for the vacancy, regardless of age, gender, origin, sexual orientation or physical ability. Commercial activities in response to this ad are not appreciated.

Core Responsibilities

Develop a physics-informed machine learning approach that combines simulations of semiconductor measurement processes with inverse reconstruction to infer nanoscale physical properties from limited, noisy, and low-resolution data. Investigate how measurement choices and configurations can be optimized to improve the reliability of parameter reconstruction, in collaboration with ASML and academic research partners.

Requirements

Applicants must have or be close to completing a master's degree in computer science, machine learning, artificial intelligence, applied mathematics, physics, or a related discipline, meeting Dutch PhD-entry requirements. A background in machine learning, inverse problems, scientific computing, or related data-driven methods is desirable; strong analytical and collaborative skills and proficiency in spoken and written English are essential.

Benefits

• Employment benefits
• PhD courses
• Housing and visa application assistance
• Transport cost compensation
• Furnishing expense compensation