As a Software Development Engineer on our on-robot software team, you will help our robots know where they are and get where they need to go. You will partner with applied scientists working on localization and mapping (SLAM), spatial memory, and navigation to turn their algorithms into fast, reliable on-robot components. You will integrate them with perception, task planning, and safety, and measure how well they work on real robot data. Our robots work in large, busy, and changing spaces, where a robot that loses track of where it is can't do its job.
Join us in building the next generation of intelligent robotics systems that will transform the future of automation and human-robot collaboration.
Key job responsibilities
- Partner with scientists and engineers to turn SLAM, mapping, and navigation algorithms into production on-robot components
- Build the localization and mapping pipeline, and keep the robot localized over long distances in large spaces that change throughout the day
- Build the spatial memory that records what the robot has seen and where
- Make navigation reliable alongside perception and safety, including recovering when the robot gets stuck
- Measure how well localization and navigation work on real robot data, and use that to improve them
- Make it all run in real time on the robot's embedded compute, and debug failures on real robots
- Write design docs and experiment reports that are clear about tradeoffs and limitations
BASIC QUALIFICATIONS
- 3+ years of non-internship professional software development experience
- Experience programming with C++ and/or Python
- Experience developing or integrating perception, SLAM, localization, or navigation software for robots, autonomous vehicles, or other real-world systems
PREFERRED QUALIFICATIONS
- Master's degree or PhD in Robotics, Computer Science, Electrical Engineering, or a related field, with a focus on state estimation, computer vision, or robotics
- Experience with SLAM and state estimation, such as visual, visual-inertial, or lidar odometry, loop closure, pose-graph optimization (e.g., GTSAM, Ceres, g2o), and localization in prebuilt maps
- Experience with navigation stacks (e.g., ROS 2, Nav2, costmaps, global and local planners, behavior trees)
- Experience with 3D data and point clouds (e.g., PCL, Open3D) and occupancy or voxel mapping
- Experience building semantic maps, scene graphs, or spatial memory for robots, including with vision-language models
- Experience with multi-sensor pipelines, time synchronization, and coordinate-frame management (e.g., cameras, lidar, IMU, tf2)
- Experience taking research algorithms from prototype to production, including porting Python prototypes to production C++
- Experience optimizing SLAM, perception, or machine learning workloads for real-time performance on embedded CPUs and GPUs (e.g., NVIDIA Jetson, CUDA)
- Experience building simulation-based or hardware-in-the-loop evaluation for localization or navigation
- Experience using AI coding assistants and agents to speed up development, with sound judgment about reviewing and verifying their output
- Excellent collaboration and communication skills, with the ability to work across science and engineering teams
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.
USA, MA, N.Reading - 143,700.00 - 194,400.00 USD annually
