Robotics Software Engineer – On-Robot AI & Perception

Amazon; Massachusetts; On-site; USD 144,000 - 194,000; Full time

Job summary

Amazon.com Services LLC is seeking a Software Development Engineer to join the on-robot software team. You will work with perception, SLAM, and navigation experts to integrate models into the robot’s onboard software and run in real time on embedded GPUs, turning research into reliable, production-ready components.

Join us to build the next generation of intelligent robotics at scale, and contribute to evaluation loops, datasets, and metrics that drive measurable improvements in accuracy and

Qualifications

• 4+ years in CS, ME, EE or related field experience.
• Knowledge of Python and/or C++ programming.
• Experience with robotics middleware like ROS2, ZCM, Zenoh, etc.
• Experience deploying and optimizing machine learning models for real-time inference on embedded or edge GPUs (e.g., NVIDIA Jetson).
• Experience with test driven development (TDD) in robotics software.

Responsibilities

• Partner with perception, SLAM, and navigation scientists to integrate models into on-robot software.
• Optimize deep learning models and CV pipelines for real-time inference on embedded GPUs.
• Profile and reduce perception latency, throughput, and memory use from sensor input to model output.
• Build multi-camera and multi-sensor data paths with zero-copy processing.
• Create evaluation datasets, metrics, and regression gates for accuracy improvements.
• Make perception components production-ready with versioning, health monitoring, and telemetry.

Skills

Python

C++

ROS2

Embedded GPUs

TDD in robotics

Education

Master's degree in Robotics/CS/EE

PhD in Robotics/CS/EE

Tools

TensorRT

ONNX Runtime

CUDA

Nsight Systems

Nsight Compute

Jetson

Job description

Amazon.com Services LLC is seeking a Software Development Engineer to join the on-robot software team. You will work with perception, SLAM, and navigation experts to integrate models into the robot’s onboard software and run in real time on embedded GPUs, turning research into reliable, production-ready components.

Join us to build the next generation of intelligent robotics at scale, and contribute to evaluation loops, datasets, and metrics that drive measurable improvements in accuracy and