Applied Scientist: Real-Time VIO & Perception for Robots

Amazon; New York (NY); On-site; USD 172,000 - 223,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Job summary

Amazon.com Services LLC in New York is seeking an Applied Scientist to develop and optimize Visual Inertial Odometry (VIO) and sensor fusion systems for intelligent robots. You will design, implement, and deploy state estimation and tracking algorithms for real-time perception on resource-constrained hardware.

This hands-on role involves working with sensors, embedded devices, and real data, collaborating with hardware and controls teams to push ML-based perception alongside classical geometric

Qualifications

• PhD or Master's degree with 3+ years of applied research experience.
• Hands-on experience developing and deploying Visual Inertial Odometry or visual-inertial SLAM systems.
• Experience with multi-sensor fusion and state estimation (EKF, factor graphs).
• Experience optimizing perception algorithms for embedded hardware.
• Proficiency with real sensor data and calibration on physical robots.
• Familiarity with modern ML approaches to perception (learned features, depth estimation, end-to-end odometry).

Responsibilities

• Design and implement Visual Inertial Odometry algorithms for real-time state estimation on robotic platforms.
• Develop multi-sensor fusion pipelines for cameras, IMUs, and other modalities.
• Optimize perception and tracking for embedded hardware under latency and power constraints.
• Apply ML-based perception to complement geometric estimation methods.
• Build and maintain calibration, evaluation, and benchmarking infrastructure.
• Collaborate with hardware, controls, and navigation teams to integrate perception outputs.
• Lead technical projects from research prototyping to production deployment.

Skills

Python

C++

Machine learning

Robotics

VIO/SLAM

Embedded systems

Calibration with real sensors

Education

PhD

Master's degree in related field

Tools

ROS/ROS2

Jetson

Embedded hardware

Job description

Amazon.com Services LLC in New York is seeking an Applied Scientist to develop and optimize Visual Inertial Odometry (VIO) and sensor fusion systems for intelligent robots. You will design, implement, and deploy state estimation and tracking algorithms for real-time perception on resource-constrained hardware.

This hands-on role involves working with sensors, embedded devices, and real data, collaborating with hardware and controls teams to push ML-based perception alongside classical geometric