PhD – Predictive Occupancy World Models for Autonomous Driving

About the role

Join Bosch Research Computer Vision and AI Lab in Hildesheim as a PhD candidate focused on predictive occupancy world models for end‑to‑end autonomous driving. You will contribute to cutting‑edge AI research that enables safe and transparent vehicle navigation.

Key responsibilities

• Design and implement a generic predictive occupancy model that captures geometry and semantics of all traffic participants.
• Develop end‑to‑end driving architectures that directly use the occupancy world model for decision making.
• Create perception pipelines that transform raw sensor data into rich spatial representations.
• Evaluate models in simulation environments (e.g., CARLA) and with real‑world datasets, measuring safety, transparency and performance improvements.
• Publish research results at leading AI and robotics conferences.

Required profile

• Excellent master’s degree in Computer Science, Robotics, Artificial Intelligence, Data Science or a related field, qualifying you for doctoral studies.
• Strong expertise in deep learning and computer vision, with hands‑on experience using modern frameworks such as PyTorch.
• Proven Python programming skills and familiarity with 3D computer‑vision concepts.
• Creative, self‑driven researcher who thrives both independently and in technical discussions.

Required skills

• Deep Learning
• Computer Vision
• Python
• PyTorch
• 3D Computer Vision
• Occupancy Networks
• End‑to‑End Driving
• World Models
• Sensor Fusion
• Simulation environments (e.g., CARLA)

What we offer

• Opportunity to work at the forefront of autonomous‑driving research within a global technology leader.
• Access to state‑of‑the‑art labs, datasets and simulation tools.
• Support for publishing and presenting research at top conferences.