Senior 3D Perception Scientist - Robotics & Edge Inference

Amazon Science; Seattle (WA); On-site; USD 167,000 - 226,000; Full time

Benefits offered by this job

Medical/Dental/Vision

Paid PTO

401(k) Plan

Job summary

Amazon Robotics seeks a Senior Applied Scientist to advance scalable 3D perception for real‑time robotic systems. You will craft encoder‑decoder and transformer architectures for semantic occupancy and scene completion on robotic platforms, while optimizing latency for edge devices.

You will also lead and mentor a team of scientists, drive data-generation pipelines, and push concepts from research to production across fulfillment networks.

Qualifications

• PhD or Master's degree with 6+ years of applied research experience.
• Proficiency in Java, C++, Python or related languages.

Responsibilities

• Architect, design, and implement 3D perception models for semantic occupancy prediction and scene completion on robotic platforms.
• Own end-to-end model lifecycle: develop scalable training pipelines, optimize inference latency for ARM-based edge processors, and deploy production models.
• Design and scale pseudo-ground-truth data generation pipelines using SageMaker infrastructure.
• Drive multi-view perception integration by fusing multiple view camera inputs for robust 3D reconstruction.
• Influence the team's technical strategy and contribute to the long-term vision for 3D perception in fulfillment robotics.
• Mentor applied scientists and engineers, leading a culture of scientific rigor and rapid experimentation.
• Prototype and validate concepts through simulation and live robotic workcell testing.

Skills

Java

C++

Python

Education

PhD

Master's degree

Tools

R

scikit-learn

Spark

MXNet

TensorFlow

NumPy

SciPy

Job description

Amazon Robotics seeks a Senior Applied Scientist to advance scalable 3D perception for real‑time robotic systems. You will craft encoder‑decoder and transformer architectures for semantic occupancy and scene completion on robotic platforms, while optimizing latency for edge devices.

You will also lead and mentor a team of scientists, drive data-generation pipelines, and push concepts from research to production across fulfillment networks.