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’ll be doing
As a Robotics Platform Engineer you are responsible for making our software run reliably and performant on the NVIDIA Jetson.
Architect and implement heterogeneous computing strategies to balance workloads across the Jetson’s CPU, GPU, and DLA, ensuring optimal utilization of unified memory to minimize data transfer overhead.
Lead the deployment and optimization pipeline for RL policies and neural networks, focusing on low-latency execution and deterministic performance in highly dynamic environments.
Use profiling tools to characterize the system and manage the NVIDIA Jetson resources to ensure predictable performance of the entire SW stack. Identify the sources of issues, propose and implement mitigation strategies.
Inform architectural solutions that allow the platform to seamlessly scale while maintaining performance.
What you must have
Bachelor's or Master's degree in Computer Science, Electrical Engineering, or Robotics.
At least one full year of hands-on experience managing resource allocation and prioritization between CPU and GPU workloads.
Ability to understand large C++ and python codebases used in robotics.
Experience with common ML toolkits such as. CUDA and tensorrt
Demonstrated experience successfully running and deploying complex software and RL policies onto embedded Linux systems (Jetson/edge computing).
Strong ability to diagnose and solve problems when deployed software/RL policy execution fails on the embedded hardware.
Get some bonus points
Proven ability to debug complex software running on embedded hardware (specifically Jetson).
Deep understanding of Linux kernel internals (specifically scheduling and memory management) as they relate to high-performance embedded systems.
Experience with NVIDIA DeepStream or Isaac ROS for hardware-accelerated perception pipelines.
Practical experience with model optimization techniques (e.g., precision calibration, layer fusion) to maximize hardware-accelerated throughput.
Experience implementing Continuous Integration/Continuous Deployment (CI/CD) practices for embedded systems.
