Responsibilities

• Design, train, and deploy perception systems for object detection, segmentation, depth estimation, and 3D scene reconstruction
• Build multi-modal pipelines fusing RGB, depth, and inertial data into robust real-time representations
• Develop vision models that transfer reliably from simulation to physical hardware
• Optimize inference pipelines for embedded compute constraints
• Partner with navigation and manipulation teams to ensure perception outputs meet downstream needs
• Drive systematic evaluation on hardware and iterate on failure modes

Requirements

• Strong foundations in computer vision, 3D geometry, and deep learning
• Hands-on experience building perception systems for physical robots or real-time embedded platforms, gained through industry or research work
• Proficient in Python and C++, with strong PyTorch or JAX experience
• ...