Intern (Master's Thesis) Manufacturing

As a German subsidiary of the Ford Motor Company, Ford-Werke GmbH shapes the future of mobility. In the Global Operations area, teams worldwide work on making production processes efficient and future-oriented.

The ATP (Advanced Industrial Technology and Platforms) organisation deals with innovations in manufacturing.

Responsibilities

Your tasks will include:

• Preparing, checking, and analysing real production data, including data cleaning, feature extraction, and visualisation
• Comparing and correlating real production data with existing process and simulation models, as well as relevant quality characteristics
• Building and adapting a data-based model that reflects real production conditions and process fluctuations
• Analysing the model's generalisability across different production conditions, plants, or materials, and identifying limiting factors
• Investigating and evaluating suitable transfer learning approaches to efficiently adapt existing models to new production domains and reduce required training effort
• Validating the model's quality using real production data and assessing its potential for scalable industrial application

Qualifications

Requirements include:

• Studying mechanical engineering, industrial engineering, physics, computer science, computational engineering science, or a similar field
• Good knowledge of Python and previous work experience in data science and machine learning
• Familiarity with data processing and visualisation; experience with industrial or production data is beneficial
• Analytical, structured, and independent work style
• Teamwork and enthusiasm for collaboration with Ford and Fraunhofer ILT
• Excellent German and/or English language skills in writing and speaking

Benefits

Benefits include:

• A challenging thesis at the interface of AI, manufacturing, and real industrial production
• Collaboration with Global Operations within the ATP organisation and Fraunhofer-Institut für Lasertechnik ILT
• Access to real production data and insights into innovative manufacturing technologies