MSc in Data Science, Artificial Intelligence, Biomedical Engineering or related- Diagnosing print quality anomalies through machine learning with synthetic data
Are you a MSc student which is looking for a graduation assignment/internship? Are you ready for the challenge to improve our diagnostics by creating synthetic data, bringing real impact for the company? We are looking for you!
Your assignment
Due to the large variety, scale, and difference in visibility of print quality artefacts, it remains difficult to detect them reliably using classical image processing techniques alone. To address this limitation, we explore the use of machine learning methods. However, previous attempts have shown that training on real-world data is challenging, mainly because this data is largely unlabelled and highly variable.
In this project, you will therefore focus on constructing a representative synthetic dataset that captures the essential characteristics of real print artefacts. This dataset will then serve as the foundation for developing robust models that can generalize to real-world printer data. The synthetic data will be derived and validated against measurements obtained from high-end production printers operating in professional print environments worldwide. As such, your work will contribute directly to improving diagnostic capabilities and enabling more efficient service support for customers.
The exact scope of the project is aligned with the duration and type of assignment you choose.
1. For an internship project, the emphasis will be placed on the creation of the synthetic dataset. You will study real artefacts, translate their characteristics into a controllable data generation process, and ensure that the resulting dataset is both representative and usable. This requires a combination of data analysis, modelling, and validation against real measurements.
2. For a longer graduation assignment, the scope is extended beyond dataset creation. In addition to building the synthetic dataset, you will design, train, and evaluate a machine learning model that can diagnose print-quality artefacts on real-world data. This includes defining appropriate model architectures, training strategies, and validation methodologies to ensure that the model performs reliably under realistic conditions.
Throughout the project, you will be guided by experienced engineers and researchers from the R&D department, ensuring that your work remains closely connected to real industrial challenges and has tangible impact.
Your profile
- You are currently pursuing a master’s degree in data science, Artificial Intelligence, Biomedical Engineering, or a related field.
- You enjoy working with complex and imperfect datasets and see it as a challenge to extract meaningful patterns from them. You are comfortable with programming (preferably Python) and have experience with data analysis, statistics and machine learning.
- You are enrolled at a university and are looking for an internship or graduation assignment that is a mandatory part of your curriculum, for which you will also receive credits.
- As of September 2026, you are available for 4 to 12 months, for a minimum of 4 days per week.
What’s in it for you?
- A challenging assignment with skilled coaching
- Internship/ Graduation compensation of €500,- per month
- Travel cost compensation if you don’t have an ‘OV-weekcard’
- The possibility to network with professionals inside and outside your field of expertise, thanks to our diversity of disciplines which you will work with
Interested?
Are you interested in this assignment? Please click on the button 'apply now' where you can upload your resume and motivation letter.
Please note that applications can be submitted until July 10 . After this date, a selection of candidates will take place, followed by feedback on whether an interview will be scheduled.
