The ideal candidate will be responsible for developing robust and high-performance SLAM and sensor fusion systems for autonomous robotics, navigation & mapping. They will design and implement scalable, testable, and modular code in C++ within the ROS1/ROS2 ecosystem , integrating various sensors and building real-time, production-grade state estimation and mapping pipelines . Responsibilities Design and implement advanced SLAM and sensor fusion algorithms in C++ using ROS1 / ROS2. Integrate and calibrate sensors like LiDAR, IMU, GPS, and Cameras , to build robust state estimation pipelines. Integrate and develop custom drivers, ROS nodes, and message filters for real-time robotic systems. Use GTSAM, Ceres Solver, or similar tools for graph optimization and sensor fusion. Build scalable and reusable ROS1 / ROS2 packages for perception, localization, and mapping. Test algorithms both in simulation (Gazebo, RViz) and on physical robotic platforms . Collaborate closely with hardware and embedded teams for system-level integration. Maintain high coding standards with unit tests, ROS test coverage, and CI integration . Document code, algorithms, and interfaces to support collaborative development. Required Skills Strong proficiency in Modern C++ (C++14/17/20) with deep understanding of memory management, STL, multithreading, and templates. Hands-on experience with SLAM (e.g., LIO-SAM, ORB-SLAM) and sensor fusion techniques. Proficiency in ROS (ROS 1 or ROS 2) development and ecosystem. Strong understanding of robot kinematics , SE(3) transformations , rotation/translation matrices , and pose graphs . Experience with Ceres Solver , GTSAM , or other optimization frameworks for non-linear least squares problems. Familiarity with tools like Rviz , Gazebo , tf2 , and rosbag . Experience with Git , CMake , and writing well-documented, modular code. Solid mathematical foundation in linear algebra , probability , and optimization . Deep understanding of robotic system design and control architectures. Preferred Qualifications Bachelor's or Master's degree in Robotics, Mechatronics, Computer Science, or related field. 2+ years of experience in autonomous navigation, SLAM, or sensor fusion. Experience with PCL (Point Cloud Library) and 3D point cloud processing. Familiarity with Kalman Filters , Extended Kalman Filters (EKF) , or factor graph-based estimation . Contributions to open-source robotics projects or publications in SLAM/perception. Show more Show less