Applied Scientist - Real-Time VIO for Robotic Perception

Amazon Inc.; Seattle (WA); Presencial; USD 172.000 - 223.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

RSUs

Health insurance

401(k) matching

Paid time off

Parental leave

Descripción de la vacante

Amazon.com Services LLC is seeking an Applied Scientist to develop and optimize Visual Inertial Odometry (VIO) and sensor fusion systems for intelligent robots. You will own the full pipeline from algorithm development through embedded deployment, ensuring perception runs efficiently on resource-constrained hardware and leveraging modern ML approaches to augment traditional geometric methods.

This hands-on role involves working with sensors, hardware, and real-world data, prototyping, testing,

Formación

• Experience building models for business applications.
• Publications or patents at top-tier conferences/journals.
• Programming in Java, C++, Python or related language.
• Hands-on experience developing Visual Inertial Odometry or SLAM systems.
• Strong multi-sensor fusion and state estimation knowledge.
• Experience optimizing perception algorithms for embedded hardware.

Responsabilidades

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

Conocimientos

C++

Python

VIO

Sensor fusion

State estimation

Embedded systems

Herramientas

ROS/ROS2

NVIDIA Jetson

ARM

GPU

Descripción del empleo

Amazon.com Services LLC is seeking an Applied Scientist to develop and optimize Visual Inertial Odometry (VIO) and sensor fusion systems for intelligent robots. You will own the full pipeline from algorithm development through embedded deployment, ensuring perception runs efficiently on resource-constrained hardware and leveraging modern ML approaches to augment traditional geometric methods.

This hands-on role involves working with sensors, hardware, and real-world data, prototyping, testing,