1 day ago
Sunnyvale, CA, USAStaff+
Base Salary
$407k - $460k/yr
Responsibilities
- Design and train 3D foundation models and world models using large-scale driving data.
- Develop architectures for 3D perception, geometric reasoning, reconstruction, and world modeling across space and time.
- Build scalable data-generation and auto-labeling pipelines for geometric supervision from sensor data.
- Develop offline SLAM and 3D reconstruction pipelines for trajectories, scene geometry, calibration signals, and model supervision.
- Apply multi-view geometry, neural rendering, NeRFs, Gaussian Splatting, implicit 3D representations, and feedforward 3D modeling.
- Develop geometry-aware tokenization and representation learning across cameras, viewpoints, time, and sensing modalities.
- Build foundation vision models using camera, radar, LiDAR, and other sensor data.
- Explore video and generative modeling for scene structure, dynamics, and future evolution.
- Train and evaluate models at scale on distributed compute.
- Develop automated evaluation and ground-truth systems for geometric consistency, reconstruction quality, 3D understanding, and driving performance.
- Optimize and deploy models into production autonomous-driving systems under onboard constraints.
- Set technical direction and collaborate with foundation-model, perception, simulation, data, sensing, and deployment teams.
Requirements
- Deep expertise in 3D computer vision, geometric vision, or 3D machine learning.
- Strong experience designing, training, and evaluating modern deep-learning models at scale using PyTorch or a comparable framework.
- Strong foundations in geometry, linear algebra, probability, optimization, and 3D transformations.
- Excellent software engineering skills in Python and C++.
- Track record of taking difficult research problems from concept to working systems, including data, training, evaluation, or deployment pipelines.
- Principal-level technical leadership, including setting direction, making architectural decisions, and raising technical standards.
- Experience with multi-view geometry, dense 3D reconstruction, neural fields, NeRFs, Gaussian Splatting, or feedforward 3D models is desirable.
- Experience with vision pre-training, self-supervised learning, video models, generative models, or learned scene dynamics is desirable.
- Experience with offline SLAM, structure-from-motion, reconstruction, calibration, auto-labeling, or large-scale ground-truth generation is desirable.
- Experience with multimodal perception across camera, radar, LiDAR, and other sensing modalities is desirable.
- Experience with distributed training, large-scale experimentation, and deploying neural networks on real-time, resource-constrained hardware is desirable.
Benefits
- Full-time role based in the Sunnyvale office.
- Hybrid working policy combining office and workshop time with work from home.
- Competitive equity package.
- Inclusive interview process with accommodations available upon request.
Categories
ML EngineeringRobotics
