Applied Decision Scientist (Forecasting & Optimization)

About the role

We are seeking an Applied Decision Scientist to act as the “Quantitative Architect” for client projects, handling end‑to‑end mathematical lifecycles that combine forecasting and optimization. You will develop reusable, scalable solutions for multiple industries, translating business problems into robust Python code.

Key responsibilities

• Design predictive models (time‑series, XGBoost) and prescriptive models (LP/MIP, heuristics) to forecast demand, lead times and optimize decisions.
• Translate messy business problems from various clients into formal equations and adaptable codebases.
• Write clean, production‑ready Python code using Pyomo, Scikit‑learn, SciPy and integrate with broader software pipelines.
• Develop reusable analytical assets, algorithms and digital twins that can be quickly customized for new clients.
• Act as subject‑matter expert during client engagements, explaining mathematical concepts to non‑technical stakeholders.

Required profile

• PhD (preferred) or Master’s degree in Operations Research, Applied Mathematics, Industrial Engineering, Statistics or a related quantitative field.
• Proven expertise in both machine‑learning forecasting (time‑series) and mathematical optimization (LP, MIP, heuristics).
• Strong programming skills in Python and experience with industrial solvers such as Gurobi, CPLEX or OR‑Tools.
• Ability to abstract specific client problems into generalized mathematical models and recognize patterns across projects.
• Excellent communication skills to convey complex concepts to non‑technical audiences.

Required skills

• Python
• Pyomo
• Scikit‑learn
• SciPy
• Gurobi or CPLEX or OR‑Tools
• Time‑series forecasting (e.g., XGBoost)
• Linear / Mixed‑Integer Programming