PhD - Predictive Occupancy World Models for End-to-End Autonomous Driving

Bei Bosch gestalten wir Zukunft mit hochwertigen Technologien und Dienstleistungen, die Begeisterung wecken und das Leben der Menschen verbessern. Unser Versprechen an unsere Mitarbeiterinnen und Mitarbeiter steht dabei felsenfest: Wir wachsen gemeinsam, haben Freude an unserer Arbeit und inspirieren uns gegenseitig. Willkommen bei Bosch.

Die Robert Bosch GmbH freut sich auf eine Bewerbung!

The Corporate Research division is the heart of our innovation. You will be part of the Bosch Research Computer Vision and AI Lab in Hildesheim, Germany, at the forefront of developing the next generation of autonomous systems. We are looking for a passionate and creative PhD candidate to join our team and help shape the future of AI-driven mobility.

• You will develop a generic predictive occupancy model as the core representation of the driving scene, designing architectures that capture the geometry and semantics of all objects to enable an explicit understanding of 4D world dynamics.
• Furthermore, you will research, implement, and evaluate novel end-to-end (E2E) driving architectures based on predictive occupancy world models, ensuring robust situational awareness and safe navigation.
• You will develop state-of-the-art perception systems that seamlessly transform raw sensor data into rich spatial representations and driving actions, bridging the gap between perception and automated driving.
• As part of this role, you will create architectures in which driving decisions are directly based on predictive occupancy world models, ensuring spatially grounded and reliable actions.
• Last but not least, you will rigorously test your models in simulation and with real-world data, demonstrating improvements in safety, transparency, and performance, and you will publish your findings at leading AI and robotics conferences.

• Education: excellent master's degree in Computer Science, Robotics, Artificial Intelligence, Data Science, or a related field that qualifies you for doctoral studies
• Experience and Knowledge: strong expertise in Deep Learning and Computer Vision (CV), hands-on experience with modern deep learning frameworks ("e.g., PyTorch"), and proven Python programming skills; experience in 3D Computer Vision, Occupancy Networks, End-to-End (E2E) Driving, World Models, or Sensor Fusion is highly desirable; familiarity with autonomous driving datasets and simulation environments ("e.g., CARLA") is considered an advantage
• Personality and Working Practice: you are a creative and self-driven researcher who enjoys taking ownership of challenging topics, developing innovative ideas comes naturally to you, and you thrive both independently and in technical discussions with colleagues
• Enthusiasm: you have a genuine passion for solving fundamental AI challenges and are driven to build systems that are not only intelligent but also trustworthy and safe
• Languages: excellent English skills, German is an advantage

The final PhD topic is subject to your university.

Start: September 2026

Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity.