Applied Scientist: Real-Time RL for Fulfillment

Amazon; North Reading (MA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon in Massachusetts is hiring an Applied Scientist focused on Reinforcement Learning for real-time MHE optimization. You will design, implement and deploy RL agents, reward models, and control policies in simulation and production, working with scientists and engineers to prove impact before fleet rollout.

The role requires PhD plus hands-on RL experience, strong Python and DL framework skills, and a track record of end-to-end research-to-production execution on complex problems.

Qualifications

• PhD in CS/ML/engineering or related field.
• 2+ years building ML models or developing algorithms for business application experience.
• Experience applying RL and sequential decision-making methods to real-world control or optimization problems.
• Fluency in Python; C++ is a plus.
• Experience with PyTorch or TensorFlow and RL tooling/simulators.

Responsibilities

• Own the research and development of reinforcement learning and sequential decision making solutions spanning deep RL, policy optimization, offline/batch RL, contextual bandits, and multi-agent RL for real-time MHE control and building-wide optimization in a production environment.
• Formulate fulfillment operations problems as sequential decision-making problems, and design multi-objective reward functions that balance competing operational objectives.
• Build and leverage high-fidelity simulation environments for safe offline training, policy validation, and sim-to-real transfer before fleet-scale deployment.
• Collaborate across multiple science and engineering teams to integrate RL policies into real-time production and control systems.

Skills

Python

Reinforcement Learning

Deep RL

Policy optimization

Contextual bandits

Multi-agent RL

Offline RL

Real-time inference

Education

PhD in computer science, machine learning, engineering, or related fields

Tools

PyTorch

TensorFlow

Ray/RLlib

Gymnasium

Stable-Baselines3

MuJoCo

Isaac Gym/Omniverse

Job description

Amazon in Massachusetts is hiring an Applied Scientist focused on Reinforcement Learning for real-time MHE optimization. You will design, implement and deploy RL agents, reward models, and control policies in simulation and production, working with scientists and engineers to prove impact before fleet rollout.

The role requires PhD plus hands-on RL experience, strong Python and DL framework skills, and a track record of end-to-end research-to-production execution on complex problems.