Machine Learning Engineer: Perception
Bedrock Robotics · San Francisco, CA
About this role
**Machine Learning Engineer: Perception** **About the Role:** Bedrock is seeking experienced ML engineers to design and deploy cutting-edge 3D perception systems for autonomous construction equipment. You'll work on early fusion architectures combining Lidar and camera data, optimize models for edge deployment, and solve real-world robotics challenges. **Key Responsibilities:** • Design state-of-the-art fusion models (BEV-based transformers) for object detection and semantic segmentation • Build robust perception systems handling dynamic occlusion, particulates, and high-vibration conditions • Optimize models for embedded hardware inference and debug system-level issues • Collaborate on representations for downstream autonomous systems **Required Qualifications:** • 5+ years production ML experience (PyTorch, TensorFlow, or JAX) • Deep expertise in 3D geometry, SE(3) transformations, and sensor calibration • Practical experience with early fusion architectures (BEVFusion, TransFuser, PointPainting) • SOTA object detection with modern transformers (DETR, PETR, temporal variants) • Expert Python; comfortable with C++/Rust for systems work • Strong data intuition and understanding of ground truth quality **Bonus Skills:** • Voxel/occupancy grid or NeRF experience • Published research at ICRA, IROS, CVPR, ECCV, ICCV, CoRL, or RSS **About Bedrock:** Veteran-led team deploying autonomous systems on heavy construction equipment. Raised $350M in 2 years with first fully autonomous excavator deployments achieved. *Equal Opportunity Employer - Reasonable accommodations available*
Listing freshness
CronJobs last confirmed this listing 1d ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.