Master Thesis: Quality assessment of machine learning results

Intern / Student, Part-time ยท Munich

Your tasks
When using machine learning it is essential to determine the quality of the detection. During the training process ground truth data is available to measure the quality (accuracy, recall, IoU). When applied on unknown data (inference) there is usually no ground truth data available for evaluation. Manual quality control is not feasable as it will cover only small random parts of the output. A fully comprehensive manual check is not applicable.

Objective is to create a commercially viable approach to describe the detection quality of a neural network.
  • Machine learning (CNN, deep learning) training and inference
  • Programming with Python
  • Use of image libraries like GDAL etc.
  • visualization with GIS tools
  • Statisitcs
Areas of expertise:
  • Statistical methods
  • Bayesian networks
  • Use of machine learning techniques for quality assessment
  • Ensemble learning
Life as TerraLouper is
  • exciting to be part of a highly motivated, international top team of engineers
  • interesting to work with cutting-edge technologies, agile development practices and product-focused environment
  • office location in the heart of Munich
  • flexible working hours
  • multi-cultural team
About us
TerraLoupe is a German startup to empower autonomous mobility. We use machine learning technology to automaticcally detect objects from aerial imagery to create a 3D digital twin of the world. Located in the heart of Munich the next level of geo platform and HD mapping is getting to reality.
Your application
Thank you for considering a career at TerraLoupe GmbH. Please fill out the following form. In case you are experiencing problems with the document upload, mail your documents to

Please upload any documents that you want to include with your application. CV and cover letter are required, and you should also attach copies of your references and certificates.

Click to select multiple files or use drag-and-drop
Uploading document. Please wait.