Senior Applied Scientist, Edge Vision for Robotics

Amazon Inc.; North Reading (MA); On-site; USD 167,000 - 226,000; Full time

Benefits offered by this job

RSUs

Comprehensive benefits

Job summary

Amazon Robotics seeks a Senior Applied Scientist in North Reading, MA, to advance computer vision and ML for sensing hardware used across Amazon's robotics systems. You will collaborate with hardware engineers to shape sensor selection, compute architecture, and end-to-end perception pipelines, delivering production-ready models for edge devices.

You will own ML experimentation and validation, drive latency and power-efficient inference, and publish work to advance robotic perception in

Qualifications

• PhD or Master's degree with 6+ years of applied research experience.
• Experience programming in Java, C++, Python.
• Experience with deep learning frameworks such as PyTorch or TensorFlow.
• Experience with 2D/3D vision tasks (object detection, depth) and edge deployment.
• Experience optimizing ML models for resource constrained hardware.
• Strong written and verbal communication abilities.

Responsibilities

• Partner with hardware leaders to define sensing and compute hardware requirements.
• Develop and optimize CV and DL models for robotic perception for edge deployment.
• Lead ML experimentation and validation informing hardware decisions.
• Design benchmarking frameworks for sensing hardware performance.
• Coordinate cross-functional work to transition models from prototype to production.

Skills

Java

C++

Python

Deep learning

Computer vision

ML experimentation

Communication

Education

PhD

Master's degree

Tools

PyTorch

TensorFlow

Job description

Amazon Robotics seeks a Senior Applied Scientist in North Reading, MA, to advance computer vision and ML for sensing hardware used across Amazon's robotics systems. You will collaborate with hardware engineers to shape sensor selection, compute architecture, and end-to-end perception pipelines, delivering production-ready models for edge devices.

You will own ML experimentation and validation, drive latency and power-efficient inference, and publish work to advance robotic perception in