Support and improve a production scheduling solution for a steel coating and painting operation. You will adapt an existing optimization model; you won’t be building one from scratch.

What You’ll Do

• Reverse-engineer an existing optimization model and solver built by another team, and learn its logic, constraints and data flows
• Adapt and extend the solution for North American plant scheduling and simpler paint/coating lines
• Sequence production jobs by grouping paint colors and steel dimensions, cutting changeovers (around 20 minutes per paint change) and line downtime
• Adjust the model as operational constraints and short-notice customer orders change
• Support integration of scheduling outputs with the Oracle ERP
• Troubleshoot production issues and deliver ongoing enhancements after rollout

What You’ll Bring

• Strong Python skills, with experience implementing, modifying and troubleshooting production-grade ML or mathematical optimization solutions
• Hands-on experience with optimization solvers and machine learning platforms
• Experience tuning, retraining or reconfiguring optimization/ML models for different operational constraints
• Ability to work independently in an existing codebase with limited documentation and subject-matter knowledge
• Nice to have: Azure Machine Learning experience; a background in manufacturing scheduling, production optimization, constraint optimization or supply-chain scheduling