PhD student for PhD Machine Learning – Runtime Monitoring of Autonomous Driving Functions

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: MER0003PK0 Mercedes-Benz Group AG, one of the world's most successful automotive companies, is a leading provider of premium and luxury vehicles as well as transporters. In Group Research & Development (RD), we design future vehicle generations with innovative, high-quality products and efficient processes. We strive to develop highly automated driving systems for motorways and urban areas, using state-of-the-art technologies in our teams in Germany, India, China and the USA. In order to maintain our technological leadership and to ensure exceptional customer experiences, we are looking for talented and committed doctoral students who strengthen our development team for automated driving (AD) in Sindelfingen. Your doctorate will focus on developing a runtime monitoring system to ensure the safe operation of autonomous driving functions. Based on the empirical data from function testing, a system is to be developed that identifies unknown operating states based on vehicle sensor signals and planned behavior and thus ensures reliable and reliable operation. Their research will include the creation of a theoretical framework and practical methods for improving the safety and reliability of autonomous driving systems. The main objective is the development of a method that dynamically monitors system operation, detects errors, initiates corrective measures, while fulfilling statistical guarantees. They will work at the interface of AD system development, system testing and security, supervised by experts in this field. During your research, you will use the latest techniques of machine learning: generative methods such as multimodal language models (MLLMs), multimodal representation learning, out-of-distribution detection and conformal prediction. They have access to extensive data from system development and testing, including real and simulated records. Their results will not only improve the safety of highly automated driving, but also make a significant contribution to the research community. We strongly encourage and support the publication of your work. Your tasks: Assessment of the current state of the art in the runtime monitoring of safety-critical robotics applications, including but not limited to automated driving

Enlarge your knowledge in related areas such as representation learning, generative methods, multi-modal LLMs, statistical machine learning, machine learning with guarantees, conformal prediction and out-of-distribution detection

Development of statistical models and algorithms for monitoring system operating points

Collection and analysis of data from different test drives, including real and simulated records

Validation of the effectiveness of the developed models by available data, simulations and additional test drives

Integration of the monitoring system into test vehicles

Organization of recruitment and support of students who contribute to your research

Documentation of research results and publication in scientific articles

The doctorate can start from October 2025. Adjustment requirement is the support of the doctoral project by a university lecturer. The selection of a corresponding person is the responsibility of the doctoral student.

Excellent master degree in mathematics, statistics, computer science, machine learning, robotics or related fields

Excellent programming skills in Python or C++

Strong knowledge and deep understanding of machine learning techniques, including deep learning and the corresponding software frameworks (e.g. pytorch, tensorflow)

Experience with public cloud infrastructure (GCP, AWS or Azure).

Experience with Linux and development on Linux systems.

English language skills

Preferred qualifications... Knowledge in the field of robotics, functional testing or functional safety

Basic knowledge of ADAS/AD architectures

Excellent communication skills and the desire to work in a global team in a multicultural environment

Publication at a Machine Learning or Robotics Conference is advantageous

High intrinsic motivation to conduct top research

High self-organisation

German language skills (optional)

Additional information: Do you want to make your doctorate in cooperation with Mercedes-Benz Group AG? We offer you an international network of experts, research materials, work insights and personal mentors that will assist you as a contact person in addition to your faculty. Doctorate at a renowned university with the support of Mercedes-Benz Group AG as a non-academic partner – and use the know-how of a globally active group. Please apply exclusively online and mark your application documents as ''relevant for this application' in the online form. 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 applications for disabled people and disabled people. At sbv-sindelfingen@mercedes-benz.com you can also contact the site's severely disabled representative, which will be happy to support you in the further application process. 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). Questions about the job will be answered by Mr. Julian Wiederer from the field, at the e-mail address julian.wiederer@mercedes-benz.com.

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