Lead the development of geometric vision and 3D foundation models for Wayve's autonomous driving systems. Design, train, and deploy large-scale deep learning architectures for 3D perception, reconstruction, and world modeling. Requires deep expertise in 3D computer vision, PyTorch, and principal-level technical leadership in Python and C++.
Key Highlights
Set technical direction for geometric vision and 3D foundation models at Wayve.
Develop and scale offline SLAM, 3D reconstruction, and auto-labeling pipelines for fleet-scale data.
Deploy models into production autonomous-driving systems with real-time constraints.
Key Responsibilities
Design and train 3D foundation models and world models using large-scale driving data.
Develop model architectures for 3D perception, geometric reasoning, reconstruction, and world modeling.
Build scalable data generation and auto-labeling pipelines for high-quality geometric supervision.
Develop and scale offline SLAM and 3D reconstruction systems to recover trajectories and scene geometry.
Apply techniques in multi-view geometry, neural rendering, NeRFs, and Gaussian Splatting.
Explore geometry-aware tokenization and representation learning across multiple sensing modalities.
Train and evaluate models at scale on distributed compute infrastructure.
Develop automated evaluation and ground-truth systems for geometric consistency and reconstruction quality.
Optimize and deploy models into production autonomous-driving systems.
Set technical direction for geometric vision and collaborate with cross-functional teams.
Technical Skills Required
3D Computer Vision
PyTorch
Python
Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.
Benefits & Perks
Market-benchmarked salaries
Meaningful equity
Relocation support and visa sponsorship where applicable
Hybrid working model
Learning and development budgets
Comprehensive benefits including health insurance, dental, and enhanced parental leave
Nice to Have
Experience with dense 3D reconstruction, neural fields, NeRFs, or Gaussian Splatting.
Background in large-scale vision pre-training, self-supervised learning, or generative models.
Experience with offline SLAM, structure-from-motion, and large-scale ground-truth generation.
Expertise in multimodal perception and fusion across camera, radar, and LiDAR.
Experience with production ML systems, distributed training, and real-time hardware deployment.
Job Description
Before the detail, here's the challenge you'd help us solve.We build the embodied intelligence that moves real vehicles safely, and the ecosystem a billion machines will run on in the future. Very few people in AI can say this. Every role here, whatever the team, plugs into that.Here’s what this particular role covers.The team builds the geometric vision and 3D foundation models that underpin Wayve's autonomous driving systems, working at the intersection of large-scale deep learning, geometric computer vision, and real-world robotics to develop models that learn 3D structure and dynamics from fleet-scale sensor data.
Want the full job description?
Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn
This is a short excerpt. All rights to the full description belong to its original publisher.
