Software Engineer- Spatial Perception & CV
Posted
Spatial Perception Engineer
Robotics 3D Sensing Localization & Mapping The Role This is the spatial intelligence seat on the robotics team. You'll own everything the robot needs to understand where it is and what's around it SLAM pipelines, 3D mapping, and the geometric perception layer that feeds into navigation and interaction. You're equally comfortable digging into point cloud math and wiring up real sensor hardware on a moving platform. Day-to-Day Responsibilities
Robotics 3D Sensing Localization & Mapping The Role This is the spatial intelligence seat on the robotics team. You'll own everything the robot needs to understand where it is and what's around it SLAM pipelines, 3D mapping, and the geometric perception layer that feeds into navigation and interaction. You're equally comfortable digging into point cloud math and wiring up real sensor hardware on a moving platform. Day-to-Day Responsibilities
- Architect and maintain visual and/or lidar-based SLAM pipelines for real-time localization and map building
- Process 3D point cloud data at scale implementing filtering, segmentation, and registration workflows that hold up on real hardware
- Bring depth cameras and spatial sensors online within the ROS 2 framework, managing multi-modal sensor fusion across the perception stack
- Assess and integrate open-source SLAM and RESUME tooling (RTAB-Map, ORB-SLAM, Open3D, PCL, and others), selecting the right library for each problem rather than defaulting to a single stack
- Partner closely with the Edge AI & Perception engineer to share infrastructure, avoid duplicated effort, and keep the overall perception architecture clean
- At least 7 years building software for robotic systems
- Deep hands-on experience with ROS 2 authoring nodes, orchestrating topic/service/action patterns, and designing clean system architectures
- A systems-level perspective: you're comfortable at the boundary between hardware drivers, real-time control loops, and application-layer software
- Strong Python skills; working proficiency in C++ (able to read, modify, and extend existing codebases confidently)
- Prior experience deploying and debugging software on NVIDIA Jetson platforms (Orin, Xavier, or comparable)
- Self-directed and effective in early-stage, greenfield development environments
- Applied, hands-on background in computer vision and 3D perception built and shipped systems, not just studied the theory
- Direct experience standing up SLAM in a real robotic context (visual, lidar, or visual-inertial odometry)
- Fluent with point cloud processing libraries such as PCL, Open3D, or equivalent tooling
- Strong Python and OpenCV skills; C++ proficiency sufficient to work within and extend existing perception codebases
- Hands-on familiarity with sensor calibration workflows, coordinate frame management, and the ROS TF tree
