Student for Master's Thesis - Transfer Learning with 3D Design Data

Life is always about becoming... In life it is about going on a journey to become the best version of our future self. As we discover new things, we face challenges, master them and grow beyond us.

Apply to Mercedes-Benz and find the area where you can develop your talents individually. You will be supported by visionary colleagues who share your pioneering spirit. Joining us means becoming part of a global team whose goal is to build the most desirable cars in the world. Together for excellence.

Number: MER0003P59 Mercedes-Benz is at the forefront of the automotive industry and actively shapes the future of mobility. In the research and development department (R&D) of Mercedes-Benz Cars, we work on the next generation of vehicles and drive innovations in every field of vehicle development. By using large amounts of data and advanced digital methods and AI models for CAx, we accelerate the design and validation cycles for vehicle components. Industrial AI applications are often limited by the lack of labelled data that are specially tailored to specific tasks. This limits both the performance and the generalisation of the models. In contrast, a wealth of information is created in the life cycle of CAD data, which, however, are largely unwritten or only relevant to other but related tasks. The potential of this previously unused resource is crucial for the progress of AI technologies in the industrial environment. Techniques such as transfer learning and domain adaptation have proven to be effective approaches to bridge the gap between labeled and unlabeled or cross-domain data. These methods enable more effective knowledge transfer and representation learning, in particular in challenging scenarios such as generative 3D tasks, in which annotated data sets are particularly limited for different tasks. Possible tasks: Working on the development of deep learning models for 3D objects Development of advanced 3D transfer learning methods Analysis of pre- and post-processing techniques for 3D geometries Collection and processing of data for the internal dataset The final topics will be discussed with the university, you and us. The master thesis can begin from mid-August 2025.

Study background in computer science, software technology or a related field. Excellent programming skills (e.g. in Python). Experience with deep learning frameworks (e.g. PyTorch, TensorFlow) and related projects Knowledge in the field of 3D computer vision. Safe knowledge of German and English in word and writing. Teamability and independent working. Additional information: Of course, without formalities, we are not. Please apply exclusively online and add a CV to the application, current enrollment certificate, current grade, relevant certificates (maximum size of the appendix 5 MB) and in the online form mark your application documents as 'relevant for this application'. Further information on the setting criteria can be found here. Members of countries outside the European Economic Area may send their residence/work permit. We are particularly pleased to receive online applications of disabled people and disabled people. If you have any questions, you can also contact sbv-sindelfingen@mercedes-benz.com to the site's severely disabled representative, which will be happy to assist you in the further application process after your application. Please understand that we no longer accept paper applications and there is no claim to return. Questions about the application process will be answered by HR Services by e-mail to myhrservice@mercedes-benz.com or by phone: 0711/17-99000 (Monday to Friday between 10-12 am and 13-15 pm).

Food supplements Employee handy possible Employee discounts possible Employee participation possible Staff Events Coaching Flexible working time possible Hybrid work possible Health measures Employment Mobility offers JOBV1_EN