Applied Scientist: Large-Scale RL for Robotic Manipulation

Amazon Science; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

RSUs

Job summary

Amazon Robotics is seeking an Applied Scientist to advance reinforcement learning for manipulation across diverse, real-world environments. You will train policies in simulation at scale and transfer them to physical robots, contributing to a team that spans control, perception, and hardware.

The role emphasizes production-quality code and robust, scalable training pipelines. You will collaborate with scientists to publish research and demonstrate capabilities on real hardware, with a focus on

Qualifications

• PhD or Master’s with 4+ years in science, technology, engineering, or related field experience.
• Experience programming in Java, C++, Python or related language.
• Experience in patents or publications at top-tier peer‑reviewed conferences or journals.
• Experience training reinforcement learning or imitation learning policies for manipulation or robot control problems.
• Strong background in reinforcement learning, including reward design and training at scale in simulation.

Responsibilities

• Design and train reinforcement learning policies for non-prehensile and contact-rich manipulation, focused on diverse, demanding conditions.
• Build and scale simulation environments, training curricula, and reward formulations for policies transferable to real robots.
• Develop sim-to-real methods (domain randomization, system identification) and validate on hardware.
• Write production-quality code and own scalable training and evaluation pipelines.
• Evaluate policy behavior and failure modes, iterating between simulation and real-world testing to improve robustness.
• Collaborate with scientists and engineers across control, perception, and hardware to move ideas to demonstrated capability.
• Represent Amazon Robotics in academia through publications and presentations.

Skills

Java

C++

Python

Reinforcement learning

Imitation learning

Simulation

Policy training

Education

PhD, or Master's degree and 4+ years in STEM

Tools

Top-tier conferences/publications

Job description

Amazon Robotics is seeking an Applied Scientist to advance reinforcement learning for manipulation across diverse, real-world environments. You will train policies in simulation at scale and transfer them to physical robots, contributing to a team that spans control, perception, and hardware.

The role emphasizes production-quality code and robust, scalable training pipelines. You will collaborate with scientists to publish research and demonstrate capabilities on real hardware, with a focus on