Applied Scientist, One MHS - Software, Controls, Science
Core
Design, implement, and deploy novel decision policies and optimization models for real-time Material Handling Equipment (MHE) control and scheduling in fulfillment centers.
Role type
Senior Applied Scientist (Optimization & Reinforcement Learning)
Builds
Self-optimizing fulfillment center orchestration systems and real-time control policies for MHE.
Domain
Logistics, Supply Chain, Industrial Control
Deliverable
production ML models
Required skills
Optimization mathematics (linear/nonlinear programming, constraint programming, stochastic programming), Reinforcement Learning, Machine Learning, Python, Deep Learning frameworks, Simulation/Emulation environments
Preferred skills
Discrete-event simulation, Industrial process optimization, Large-scale model deployment, Top-tier ML/OR publications
Technologies
PyTorch, d3rlpy, Ray/RLlib, Gymnasium, Stable-Baselines3, Isaac Gym/Omniverse, MILP
Responsibilities
Formulate fulfillment and manufacturing scheduling problems as optimization tasks; Build high-fidelity simulation environments for policy validation; Integrate policies into production planning and real-time control systems; Communicate research results to technical and business audiences.
Seniority
Senior, hands-on IC