182986 Thesis Machine Learning for Automated Driving (f/m/x) Veröffentlicht: 01.09.2026 Fahrerassistenzsysteme München Neu Fahrerassistenzsysteme München München

Das ist der Job

Thesis Machine Learning for Automated Driving (f/m/x) WE CANNOT PREDICT THE FUTURE.

Darum lohnt es sich

It takes dynamic teams with outstanding technical skills to take them from the drawing board to the road. That’s why our experts will treat you as part of the team from day one, encourage you to bring your own ideas to the table – and give you the opportunity to really show what you can do.

Our team at the BMW Group develops new approaches for scalable data collection in automated driving. As part of your thesis, you support our team in developing and optimizing these models.

What should you bring along? • Studies in computer science, electrical engineering, robotics, data science, or a related field • Strong foundation in machine learning and deep learning, ideally with experience in computer vision or multi-modal learning • Proficient in Python and experienced with common ML frameworks such as PyTorch or TensorFlow • In-depth knowledge of model optimization techniques such as quantization, pruning, or distillation as well as experience with sequence models such as transformers is a plus • Interest in automated driving, sensor fusion, and embedded or edge ML deployment • Structured and precise working approach along with strong team spirit • Very good English skills; German skills are a plus Would you like to help shape compact, multi-modal AI models for automated driving?

BUT WE CAN SHAPE IT. SHARE YOUR PASSION. World-leading technologies don’t make it into a BMW until they’ve undergone one of the most challenging journeys imaginable. We focus on compact, multi-modal trigger models that reliably and precisely detect relevant driving situations.

What awaits you? • You will support the review and assessment of multi-modal approaches for scenario and concept detection, including CLIP, VideoCLIP, and BLIP. • Furthermore, you help formalize the task as a multi-label, multi-modal, temporal classification problem using image, object, and location data. • In addition, you support the definition of labeling requirements for a growing set of scenario concepts. • Moreover, you assist in designing a compact, multi-modal fusion architecture for processing multiple sensor data streams. • Furthermore, you help apply model optimization techniques such as knowledge distillation, quantization, and pruning. • In addition, you contribute to building the training and evaluation pipeline and defining suitable evaluation metrics. • Moreover, you support the assessment of onboard feasibility regarding runtime and memory footprint.

What do we offer? • Mobile work. • Apartments for students (subject to availability & only at the Munich location). Duration: 6 months Working hours: Full-time At the BMW Group, we place great importance on equal treatment and equal opportunities. Our recruiting decisions are based on the personality, experience, and skills of the applicants.

Learn more here .