Decision Scientist

We are seeking a hands-on contractor to develop, enhance, and support analytical solutions across supply risk sensing and procurement intelligence initiatives. This is an individual-contributor role requiring strong mathematical modeling, Operations Research (OR), applied machine learning/statistics, and production-quality Python skills. The person should be able to understand existing solutions, independently solve well-defined technical problems, and clearly explain their approach, assumptions, and results to the Decision Science team.

Daily tasks

• Develop and enhance mathematical optimization (LP/MILP), simulation, time-series, statistical/ML, and network-based analytical models as required by the use case.
• Formulate analytical problems clearly, including decision variables, objective functions, constraints, assumptions, and appropriate treatment of infeasibility or trade-offs.
• Work with existing Python analytical pipelines and Databricks notebooks; trace dependencies across data transformations, model logic, and downstream outputs before making changes.
• Prepare and validate analytical inputs from demand forecasts, inventory, bills of materials, supplier data, and other operational datasets.
• Develop, train, and evaluate ML models for applications such as classification, forecasting, anomaly detection, and ranking when supported by available data.
• Validate solutions through appropriate testing, scenario/sensitivity analysis, and business-result reconciliation.
• Write modular, maintainable, testable Python code; document model logic, implement regression tests, use version control, and troubleshoot data/model/runtime issues.
• Collaborate with the Decision Science, Data Engineering, and Technology teams on implementation dependencies, testing, and production readiness.

Requirements

• Master's degree in Operations Research, Industrial Engineering, Applied Mathematics, Statistics, Computer Science, or a similarly quantitative field.
• 4+ years of hands-on experience building analytical/OR/ML solutions, ideally in supply chain, manufacturing, logistics, procurement, or other operational environments.
• Strong fundamentals in optimization modeling, including LP/MILP formulation, solver behavior, and practical infeasibility handling.
• Hands-on applied ML/statistical modeling experience, including feature engineering, model training, appropriate validation design, metric selection, and interpretation of results.
• Strong Python proficiency (e.g., pandas, NumPy, and analytical libraries) and experience writing maintainable code beyond exploratory prototypes.
• Hands-on experience with an optimization modeling framework (specifically Pyomo) and LP/MILP solvers (such as GLPK or Gurobi).
• Ability to understand, debug, and extend existing code and analytical models, and communicate technical design and results clearly to the project team.

Preferred Qualifications

• Experience with Azure Databricks, PySpark/Spark, Delta Lake, and Unity Catalog.
• Background in supply network modeling, multilevel bills of materials, inventory optimization, disruption simulation, or graph-based analysis (Neo4j/Cypher is a plus).
• Experience with time-series forecasting, anomaly detection, and ML ranking/recommendation methods.
• Experience in pharmaceutical/life sciences supply chains or exposure to GenAI-enabled analytics and conversational insights.

Must have: Python, Operations Research, Mathematical Optimization, Linear Programming (LP / MILP), Pyomo, Gurobi / GLPK, Machine learning, Statistical Modeling, Supply Chain Analytics, Git

Nice to have: Azure Databricks, PySpark, Apache Spark, Delta Lake, Unity Catalog, Neo4j, Cypher