Automated driving is one of the most significant technological challenges of our time. While traditional autonomous systems rely on modular pipelines, the industry is shifting toward end-to-end learning - a paradigm that scales massively but often acts as a "black box." We are seeking an excellent PhD candidate to bridge this gap. Your goal is to be the architect of a next-generation, modular, and scalable end-to-end driving model. You will explore how to join the benefits of two competing paradigms: the data-driven power of unified models and the safety-critical explainability of decomposed pipelines. This position offers a unique bridge between academic excellence and industrial application: alongside publishing your research at top-tier venues, you will have the opportunity to see your contributions integrated into the next generation of real-world ADAS products.

Master the State-of-the-Art: As part of your role you conduct a deep-dive analysis of current breakthroughs in end-to-end autonomous driving. You will investigate how to exploit large-scale datasets without relying on labeled data for every sub-task, identifying the next frontier of innovation.

Innovate and Develop: Furthermore, you will design and implement novel deep neural network architectures that prioritize both high-performance scaling and human-interpretable explainability.

Experiment and Validate: Through rigorous experiments on public benchmarks and our massive, Bosch-owned autonomous driving datasets, you will validate the performance and reliability of your models.

From Lab to Road: In close collaboration with expert project teams in deep learning and computer vision, you will brainstorm new ideas and have the unique opportunity to deploy your software on hardware, validating your research on real automotive driving systems.

Share Your Success: We support your academic growth. You will publish your findings and research outcomes at top-tier computer vision and machine learning journals and conferences.