Robotics Evaluation Scientist

Amazon Inc.; New York (NY); Sur place; USD 172 000 - 223 000; Plein temps

Avantages offerts par ce poste

Health insurance

401(k) matching

Paid time off

Parental leave

Résumé du poste

Amazon.com Services LLC in New York seeks an Applied Scientist to design evaluation frameworks and data collection protocols for robotic capabilities. You will define how we measure, stress-test, and improve robot behavior across real-world tasks, shaping policy validation and high-quality dataset generation.

The role sits at the intersection of robotics, machine learning, and human-in-the-loop systems, building infrastructure that connects teleoperation, evaluation, and learning.

Qualifications

• 3+ years building models for business applications.
• PhD or Master’s with 4+ years in CS/CE/ML or related field.
• Publications or patents in top-tier venues.
• Experience programming in Java, C++, Python.
• Experience in algorithms, data structures, numerical optimization, data mining, parallel/distributed computing.

Responsabilités

• Design and implement evaluation frameworks for robot capabilities across tasks and real-world scenarios.
• Develop task definitions, success criteria, and benchmarking methodologies for policy evaluation.
• Create and refine data collection protocols for high-quality, task-relevant datasets.
• Build teleoperation workflows and operator interfaces for scalable data collection.
• Analyze results to identify performance gaps and data collection needs.
• Collaborate with engineering teams to integrate evaluation tooling and data pipelines into the robotics stack.
• Stay current with advances in robotics, evaluation methodologies, and human-in-the-loop learning.
• Lead technical projects from conception through production deployment.
• Mentor junior scientists and engineers.

Connaissances

Java

C++

Python

Algorithms

Data mining

Parallel computing

Distributed computing

Optimization

Formation

PhD

Master's + 4+ years

Outils

Unix/Linux

Description du poste

Amazon.com Services LLC in New York seeks an Applied Scientist to design evaluation frameworks and data collection protocols for robotic capabilities. You will define how we measure, stress-test, and improve robot behavior across real-world tasks, shaping policy validation and high-quality dataset generation.

The role sits at the intersection of robotics, machine learning, and human-in-the-loop systems, building infrastructure that connects teleoperation, evaluation, and learning.