Analyze current optical inspection processes and defect classification methods 

Identify root causes of inconsistent defect evaluations and coding errors

Assess inspection reliability using Attribute Agreement Analysis (Gage R&R)

Research best practices for visual inspection and operator guidance

Develop a standardized approach for defect evaluation and classification

Design and test digital, rule-based, or AI-supported guidance solutions 

Create and validate a prototype in a production environment 

Define a future inspection process linking defect criteria, images, and failure codes 

Evaluate the potential of AI for defect recognition and code recommendations 

Measure the impact on inspection consistency, accuracy, and quality data reliability

Master's student in Industrial Engineering, Quality Management, Data Science, Artificial Intelligence, Computer Science, or similar

Knowledge of quality tools, Measurement System Analysis (MSA), or statistical methods is considered an advantage 

Interest in manufacturing, quality systems, digitalization, decision-support systems, human-machine interaction, and Industry 4.0 

Analytical mindset and a structured problem-solving approach 

Ability to work independently and manage a project from analysis to implementation

Fluency in English is mandatory; German will be considered an asset