Sending applications for this position is currently not working. Try again later.

Master Thesis

Intern / Student, Part-time · Tübingen/Berlin/Köln/Remote

Your mission
Multi-task learning for visual quality control
Transfer learning from neural networks pre-trained on large-scale visual recognition datasets (e.g. ImageNet) has been the standard approach in computer vision for many years. However, this approach provides little benefit in situations where the image statistics deviate substantially from photographic images. One example of such a situation is visual quality control in industrial production lines. In this thesis, we will compile a large-scale dataset for visual quality control and evaluate to what extent pre-training on this dataset benefits image classification and segmentation problems in the context of visual quality control. This thesis will be carried out in collaboration with Layer7 AI GmbH in Tübingen. Possible work locations are Göttingen and Tübingen.

Supervisor: Prof. Dr. Alexander Ecker, University of Goettingen

Contrastive learning for visual quality control
In Machine Learning, self-supervised learning approaches have seen tremendous progress in the past two years. Using only cheap unlabeled data samples, these methods are able to find representations that can be adapted with only a few labels to a range of downstream tasks like object recognition. However, while these approaches are well studied for highly variable natural images, it is unclear how well these approaches transfer to other settings like visual quality control in manufacturing, where images are highly uniform and only differ in very localized aspects like scratches or dents. In this thesis, we will apply and adapt a promising set of recent contrastive and non-contrastive self-supervised learning techniques to the context of visual quality control, with a particular focus on the data augmentations necessary to find good representations. This thesis will be carried out in collaboration with Layer7 AI GmbH in Tübingen.

Supervisor: Dr. Wieland Brendel, University of Tuebingen
Your profile
  • Good mathematical understanding (in particular statistics and linear algebra)  
  • Python programming  
  • Experience with deep learning (PyTorch or Tensorflow)
Why us?
We work in flat hierarchies, value direct communication, learn a lot as a team and make important decisions together. At Layer7 you can expect the following benefits: ​
  • Independent work on projects in the field of artificial intelligence
  • Flat hierarchies, a growth perspective and very good development opportunities
  • A dynamic and motivated team with great colleagues (with experience from BCG, IBM, SAP, Cyber Valley, etc.)
  • Steep development opportunities in a rapidly growing company
  • The possibility to work flexibly in Tübingen, Berlin, Cologne or remotely
  • Regular team events
About us
Our product, Maddox AI, is an AI-based visual quality control solution, which can automate manually performed quality inspection for manufacturing companies. Maddox AI is an asset-light SaaS solution, which addresses those visual inspection tasks that are still performed manually, as conventional (=rule-based) computer vision methods fail. In product development, we closely collaborate with leading AI researchers from the Cyber Valley. Prof. Dr. Matthias Bethge, Prof. Dr. Alexander Ecker and Dr. Wieland Brendel have been researching in the field of machine learning and computer vision for years and are part of our founding team.

Maddox AI is used by DAX-30 companies as well as by large medium-sized enterprises. Our team consists of scientists, former strategy consultants, mechanical engineers, and software developers. We know that Layer7's success is only made possible by our unique team. As we continue to grow, we want to convince the best and brightest minds of our mission to establish Maddox as the modern quality management platform.
Your application!
We appreciate your interest in Layer7 AI GmbH. Please fill in the following short form. Should you have any difficulties in uploading your files, please contact us by mail at

Please upload your CV, recent certificates as well as a brief cover letter (in total max. 20 MB).

Click to select multiple files or use drag-and-drop
Click to select multiple files or use drag-and-drop

Uploading document. Please wait.