Applied Scientist: Real-Time Optimization & RL

Amazon; Seattle, Northern (WA, KY); Hybrid; USD 143,000 - 193,000; Full time

Job summary

Amazon seeks an Applied Scientist to advance optimization and sequential decision-making for real‑time MHE control and scheduling across fulfillment networks. You will design, implement, and evaluate novel decision policies and deploy them from prototype to production environments.

You will collaborate with scientists and engineers to validate policies, publish where merited, and align research with practical product goals and fleet-wide impact.

Qualifications

• PhD in Operations Research, Statistics, Applied Mathematics, Engineering, CS or related field.
• 2+ years of building machine learning models or developing algorithms for business application experience.
• Experience in optimization mathematics such as linear programming and nonlinear optimization.
• Knowledge of and proficiency in Python scripting language.
• Experience with end-to-end ownership of major project deliverables.
• Experience with popular deep learning frameworks and RL tooling (e.g., PyTorch, d3rlpy, Ray/RLlib, Gymnasium, Stable-Baselines3, Isaac Gym/Omniverse).
• Demonstrated experience developing and applying optimization or reinforcement learning solutions to real-world control, scheduling, or operation problems.

Responsibilities

• Own the research and development of optimization and sequential decision‑making solutions spanning constraint programming, stochastic and robust optimization, contextual bandits, and reinforcement learning for real‑time MHE control and scheduling optimization in a production environment.
• Formulate fulfillment operations and manufacturing scheduling problems as optimization or sequential decision‑making problems, and design multi‑objective functions balancing objectives like on‑time delivery and schedule stability.
• Build and leverage high‑fidelity simulation and emulation environments for safe offline training, policy validation, and transfer to live systems before deployment.
• Collaborate across multiple science and engineering teams to integrate policies into production planning and real‑time control systems, including guardrails and rollout.
• Communicate results clearly in writing to technical and business audiences, and contribute to the team’s external research presence through publication where merited.

Skills

Python

Machine learning

Reinforcement learning

Optimization theory

Contextual bandits

Sequential decision making

Stochastic programming

MILP

Education

PhD in Operations Research, Statistics, Applied Mathematics, Engineering, CS or related field

Tools

Python scripting language

PyTorch

RL tooling (Ray/RLlib, Gymnasium)

d3rlpy

Stable-Baselines3

Isaac Gym/Omniverse

Job description

Amazon seeks an Applied Scientist to advance optimization and sequential decision-making for real‑time MHE control and scheduling across fulfillment networks. You will design, implement, and evaluate novel decision policies and deploy them from prototype to production environments.

You will collaborate with scientists and engineers to validate policies, publish where merited, and align research with practical product goals and fleet-wide impact.