Introduction
The Applied Data Science team at ASML develops data-driven solutions that help improve the performance, reliability, and efficiency of advanced semiconductor manufacturing systems. You will work alongside experienced data scientists and collaborate with experts from different disciplines to translate complex challenges into impactful machine learning solutions. In this internship you will explore how advanced artificial intelligence methods can improve the prediction of overlay, a critical factor for semiconductor manufacturing quality and yield. This internship offers the opportunity to contribute to innovative research while gaining hands-on experience with state-of-the-art forecasting techniques.
Your assignment
In this internship, you will investigate advanced forecasting approaches that learn temporal patterns, spatial relationships, and interactions between variables directly from data. You will evaluate different modeling strategies and assess how design choices influence predictive performance. Working closely with specialists, you will build knowledge that supports future machine learning applications within ASML. Your main responsibilities will be:
- Investigate spatiotemporal forecasting methods for overlay prediction
- Develop and validate machine learning models using large-scale datasets
- Build a prototype forecasting pipeline in Python
- Compare advanced models with relevant baseline approaches
- Analyze the impact of forecasting horizon, data selection, and model complexity
- Document findings and translate results into actionable recommendations
- Present outcomes to stakeholders within the research team
This is a master’s thesis internship for minimum 5 months, minimum 4 days per week (3 days on-site). The start date of this internship is as of February 2027, but an earlier start date is also possible.
Your profile
To be suitable for the internship, you:
- Are pursuing a master’s degree in computer science, data science, applied mathematics, or applied statistics
- Have experience with spatiotemporal modeling, time series prediction, foundation models, or world models
- Have strong programming skills in Python and experience with deep learning frameworks such as PyTorch
- Are analytical and able to translate complex data into clear insights
- Are proactive, collaborative, and comfortable communicating in English, both verbally and in writing
This internship is ideal for students who want to deepen their expertise in machine learning research and advanced forecasting techniques. You will work on a real-world challenge that directly relates to semiconductor manufacturing performance. The internship offers the opportunity to learn from experienced professionals while contributing to innovative technology that enables future generations of microchips.
Other requirements you need to meet:
- You are enrolled at an educational institute for the entire duration of the internship, and you are at least 18 years old at the start of the internship;
- 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);
- You attach your cover letter with a clear motivation on why you are interested in this internship assignment in particular;
- You need to be located in the Netherlands to be perform your internship. In case you are currently living/studying outside of the Netherlands, your application shows the willingness to relocate.
Inclusion and diversity
ASML is an Equal Opportunity Employer that values and respects the importance of a diverse and inclusive workforce. It is the policy of the company to recruit, hire, train and promote persons in all job titles without regard to race, color, religion, sex, age, national origin, veteran status, disability, sexual orientation, or gender identity. We recognize that inclusion and diversity is a driving force in the success of our company.
Do you want to know more about the internship allowance, visa support and applying for an internship at ASML? Read this page.