About the role
Amazon RIVR is a robotics company pioneering Physical AI through real-world doorstep delivery. Founded in 2024 as an ETH Zurich spin-off, RIVR developed wheeled-legged robots designed to operate in complex, unstructured environments such as stairs, gates, doors, and uneven urban terrain. We believe that achieving general physical intelligence requires solving real customer problems in the real world, where robots can learn from rich operational data at scale.
Following our acquisition by Amazon in March 2026, we are continuing this mission with greater reach and speed. By combining custom robot hardware, onboard autonomy, and cloud-based coordination, Amazon RIVR is building the next generation of safe, reliable autonomous robots for last-mile delivery
What you will be doing
Design, validate, and improve algorithms on challenging real-world data, specifically analyzing the impact of offline and online calibration on the performance of Amazon RIVR’s systems.
Contribute to the development, maintenance, and performance tracking of calibration systems on robots, ensuring the rest of the stack performs well.
Explore and integrate state-of-the-art sensors in future platforms, with focus on effective calibration strategies.
Work towards combining geometry and learning techniques for advanced sensor calibration.
Create and maintain documentation and best practices to streamline knowledge sharing for calibration procedures.
What you must have
Master’s degree in a relevant field such as Engineering, Robotics, Machine Learning, Computer Science, or a similar discipline.
A minimum of 2 years of industry or research experience.
Strong mathematical fundamentals including linear algebra, vector calculus, probability theory, and mathematical optimization.
Proven expertise in sensor calibration (e.g., camera/LiDAR intrinsic/extrinsic, temporal synchronization), and experience with various calibration methods.
Background in robotics or autonomous driving, with experience in areas such as 3D visual or LiDAR SLAM, structure from motion, factor graphs, filtering, or Bayesian estimation.
Ability to write production-level code in modern C++, and prototype efficiently in Python.
Get some bonus points
Familiarity with online or self-calibration techniques for robotics platforms.
Publications at top-tier conferences.
Experience with ROS/ROS2.
