PhD Thesis - Scalable and explainable End2End Driving Model (SEED)
Core
Architecting a next-generation, modular, and scalable end-to-end driving model that bridges data-driven unified models with safety-critical explainability for real-world ADAS products.
Role type
PhD Researcher (End-to-End Autonomous Driving)
Builds
Novel deep neural network architectures for autonomous driving integrated into real automotive driving systems
Domain
Autonomous Driving / Computer Vision / Deep Learning
Deliverable
production ML models
Required skills
Computer vision, 3D vision, machine learning, deep learning, Transformers, Sparse and BEV Queries, TensorFlow, Pytorch, Python
Preferred skills
Experience with large-scale datasets, ability to work without labeled data for every sub-task, hardware deployment experience
Technologies
TensorFlow, PyTorch, Python
Responsibilities
Conduct deep-dive analysis of current breakthroughs in end-to-end autonomous driving; Design and implement novel deep neural network architectures; Validate model performance and reliability on public benchmarks and Bosch-owned datasets; Collaborate with expert project teams to deploy software on hardware; Publish research findings at top-tier venues