Senior Perception Scientist for Safe Autonomy

Amazon; Pasadena (CA); On-site; USD 199,000 - 269,000; Full time

Job summary

Amazon is seeking a Principle Applied Scientist to lead perception for Compass safety systems. You will own perception inputs, build real-time predictive models, and guide the safety architecture across teams—controls, planning, and firmware. The role emphasizes advancing environment understanding beyond static scenes to support safe robot operation.

You will mentor researchers, publish at top venues, and influence organizational strategy for safety in robotic perception.

Qualifications

• PhD in a technical field with robotics focus.
• Strong publications in top venues are preferred.
• Experience deploying perception systems on robots.

Responsibilities

• Define long-term scientific vision for safe perception across platforms.
• Develop real-time perception algorithms for dynamic environments.
• Ensure perception outputs align with safety constraints and guarantees.
• Quantify and bound perception uncertainty with calibrated estimates.
• Architect pipelines across sensor modalities and robot morphologies.
• Collaborate with controls and planning teams to define interfaces.
• Publish research and mentor a team of scientists.

Skills

3D scene understanding

Object detection

Motion prediction

Python

C++

Robotics perception

Education

PhD in Electrical Engineering, Computer Science, Mathematics, or related field

Tools

ROS

TensorFlow/PyTorch

Job description

Amazon is seeking a Principle Applied Scientist to lead perception for Compass safety systems. You will own perception inputs, build real-time predictive models, and guide the safety architecture across teams—controls, planning, and firmware. The role emphasizes advancing environment understanding beyond static scenes to support safe robot operation.

You will mentor researchers, publish at top venues, and influence organizational strategy for safety in robotic perception.