Foundation is seeking an AI Engineer to build and maintain the foundational SLAM (Simultaneous Localization and Mapping) system for a humanoid robot operating in unstructured, real-world environments. You will create custom, embodied solutions from the ground up to enable centimeter-level precision localization and real-time mapping in dynamic settings like floors, stairs, cluttered rooms, and outdoor terrain.

What You'll Do

Build and maintain accurate, real-time maps of dynamic environments for a humanoid robot.
Simultaneously localize the robot with centimeter-level precision.
Develop custom, embodied SLAM solutions from the ground up for full-body humanoid operation across complex terrains.
Scale the autonomy stack by making the SLAM infrastructure layer production-ready.

What We're Looking For

Deep knowledge in vision for robotic systems.
Hands-on experience implementing SLAM pipelines in C++ and Python, building and tuning these systems end-to-end.
Strong working knowledge of modern SLAM frameworks (e.g., ORB-SLAM3, RTAB-Map, Cartographer, LIO-SAM, KISS-ICP).
Ability to extend or rewrite core SLAM framework components.
Experience with neural or learned SLAM approaches (e.g., DROID-SLAM, iMAP, NeRF-SLAM).
Experience with legged or humanoid-specific odometry challenges.
Comfort with probabilistic state estimation, Kalman filtering (EKF/UKF), and particle filters for real-time localization under uncertainty.
Familiarity with loop closure detection methods and place recognition networks.
Familiarity with strategies for long-term map consistency in changing environments.
Hands-on experience with simulation environments (e.g., Isaac Lab, MuJoCo) for development, testing, and sim-to-real validation.