Computer Science | Applied Physics internship: explaining neural network models by visualization

Join the In-Device Metrology (IDM) Team: Internship Opportunity

Introduction

The In-Device Metrology (IDM) team develops advanced solutions to inspect the quality of semiconductor patterns printed on production wafers. This is achieved through data-driven mathematical models that link physical parameters to optical signals. The accuracy of these models is critical for reliable measurements. By understanding how optical signals encode physical information, we gain deeper insights that enable continuous improvement of model performance. As an intern, you will contribute to this mission by creating tools that make complex neural network models more transparent and explainable.

Your Assignment

In this internship you will design and implement a software tool to visualize and explain neural network models used in IDM. These models map high-dimensional optical responses to physical parameters of semiconductor stacks. While linear mappings are easy to interpret, complex models (such as neural networks) require advanced techniques to identify which parts of the signal contribute most to specific parameters. This assignment offers hands-on experience in machine learning, explainable AI, and semiconductor metrology within a high-tech environment.

Key deliverables include:

• Investigating best practices for explainable neural networks (e.g., saliency maps) and adapting them for IDM data.
• Analyzing feature contributions in two trained neural networks, each based on data from differently sized wafer targets, and assessing potential overfitting.
• Applying similar analysis to a trained CNN model and reporting which features are most important and how convolutional kernels extract them.

This is a (thesis) internship with a minimum duration of 3 months. It requires an investment of 32-40 hours per week, out of which 2-3 days per week are onsite in Veldhoven. The starting date of this internship is flexible.

Your Profile

To be a perfect match you:

• Are a bachelor or master student in Computer Science, Applied Mathematics, Applied Physics, or a related field.
• Have experience with machine learning and are familiar with common ML tools.
• Have affinity with physics, metrology, and mathematical modeling.
• Are proactive, independent, and able to collaborate effectively in a team.
• Communicate clearly and are fluent in English, both verbally and in writing.

Other requirements you need to meet:

• You are enrolled at an educational institute for the entire duration of the internship;
• You need to be located in the Netherlands to be able to perform your internship. In case you’re currently living/studying outside of the Netherlands, your CV/motivation letter includes the willingness to relocate.
• If you are a non-EU citizen, studying in the Netherlands, your university is willing to sign the documents relevant for doing an internship (i.e., Nuffic agreement).

This position requires access to controlled technology, as defined in the United States Export Administration Regulations (15 C.F.R. § 730, et seq.). Qualified candidates must be legally authorized to access such controlled technology prior to beginning work. Business demands may require ASML to proceed with candidates who are immediately eligible to access controlled technology.

About ASML

ASML is a leading supplier of lithography equipment, used by the world’s top chipmakers to print microchips that are increasingly powerful, fast and energy efficient. Working at ASML is inspiring, no matter what field you're in. That’s because we push the boundaries of technology: if it’s moving the world forward, chances are, we’re behind it. In fact, we’re probably a part of the electronic device you’re using right now. We’re a global team of more than 32,000 people from 122 different nationalities and counting. Headquartered in Europe’s top tech hub, the Brainport Eindhoven region in the Netherlands, our operations are spread across Europe, Asia and the US.