Msc: Data Science - Intelligent Diagnostic Assistant: Apply Causal AI to Solve Print Quality Issues

Msc: Data Science - Intelligent Diagnostic Assistant: Apply Causal AI to Solve Print Quality Issues

Company: Canon Production Printing

Are you a MSc data science student who is looking for a graduation assignment? Are you a tech-savvy MSc IT student eager to apply AI in real-world diagnostics? Do you want to revolutionize how our service technicians world-wide identify and solve printer issues using intelligent systems? We are looking for you!

Your assignment
Canon Production Printing (CPP) develops and produces a variety of commercial size printers for the business-to-business market. Our inkjet printers are designed for high volume printing through a combination of high speed and low operational costs, while retaining high quality and flexibility.We like you to develop an intelligent diagnostic method and prototype tool to support our field technicians in efficiently identifying the root causes of print quality issues. The solution should aim to minimize diagnostic time and cost while maximizing accuracy.

The core objective is to translate our domain expertise into a structured set of models that capture cause-and-effect relationships, taking into account historical data and field feedback from technicians to enable a data-driven, adaptive diagnostic process.

Your challenges include:

• Model Development: Design and implement models that represent the causal relationships underlying print quality issues. These models should be capable of evolving through expert knowledge and continuous learning from field feedback (self-learning mechanisms). Design a feedback loop that enables the models to improve over time through technician field feedback.
• Selection of causal inference technique: Evaluate and advise on the applicability of Bayesian networks or alternative causal AI methodologies for this diagnostic context.
• Prototype Implementation: Develop a proof-of-concept tool that leverages the selected model(s) and real-world data to guide technicians through a step-by-step root cause analysis of print quality artifacts.

Your Profile:

• You are currently studying for a Master's degree in Artificial Intelligence, Data Science, Computer Science, or a related field.
• You think it’s a challenge to apply Bayesian networks or causal AI to real-world technical problems and want to see your models make a real impact.
• You are curious, analytical, and not afraid to dive into complex systems like print quality diagnostics.
• You have at least basic Python and SQL knowledge
• You are interested in translating technical models into practical tools or prototypes.
• Good communication skills — you’ll be working with both engineers and service experts.
• As of September 1st, 2025 you are available for 5 to 6 months for a minimum of 4 days per week

The assignment will be carried out at our Service & Support LFG department, with hybrid working options available.

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

What do we stand for?

We develop and manufacture high-tech printing products and workflow software for the commercial printing market as part of Canon, a global leader in imaging technologies. With around 3,300 employees across three continents and our headquarters in Venlo, the Netherlands, we innovate to create high-quality solutions that add color to the world. Guided by the philosophy of Kyosei—living and working together for the common good—our culture is built on openness, collegiality, trust and stability. We empower our people to grow, take initiative, and make an impact.
With our company values collaboration, innovation and ownership, we strive to bring out the best in each other, expand boundaries and feel empowered to take ownership of our work.