SLAM Software Engineer, Rivr

Job description

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. Operating daily in diverse urban environments, RIVR's robots continuously learn from and navigate the millions of scenarios encountered during deliveries. By owning the full stack from software to hardware, RIVR is purpose-built for safety, reliability, and the customer from day one.

Our robots require precise and real-time localization, which they achieve by utilizing onboard sensors such as IMUs, lidar, cameras and GNSS. In environments without existing maps, the robot must dynamically create a map while simultaneously localizing itself within it. As our next SLAM Engineer on a growing team, you will be an expert in laser- and camera-based localization techniques and SLAM and enhance these capabilities.

You will shape our robots’ ability to navigate with pinpoint precision, and you will be part of a team focused on enabling our robots to navigate autonomously. If you are passionate about robotics and driven to innovate in SLAM and localization, we encourage you to join us in shaping the future of intelligent robotics.

Key job responsibilities

Develop state-of-the-art, online and offline localization and SLAM algorithms by fusing information from cameras, LiDARs, IMU, GNSS, and other sensors.

Design, validate, and improve algorithms on challenging real-world data.

Contribute to the dynamic mapping of the environment using data continuously gathered from ongoing robot deployments.

Assist in the creation of robust sensor calibration systems that perform reliably in complex and unpredictable environments.

Support the development of an efficient workflow to accurately capture ground truth data, and maps of deployment sites for algorithm evaluation.

Contribute to the implementation of deployment-ready code for the real robot, optimized for the robot’s computational constraints.

Create and maintain documentation and best practices to streamline knowledge sharing.