Role Overview
We are looking for a skilled ML Engineer to design and build a robust, interpretable, and scalable optimization engine that enables data-driven pricing decisions.
The engine will leverage SKU-level demand, elasticity, and profitability data to recommend optimal pricing strategies based on business goals.
Key Responsibilities
- Refactor and enhance the existing optimization logic for speed, scalability, and modularity.
- Model price-volume relationships using elasticity inputs at SKU and brand levels.
- Develop optimization logic using constrained techniques (e.g., linear/quadratic programming).
- Integrate business rules and constraints such as price bounds, SKU/brand-level caps, and TDP limits.
- Enable scenario-based optimization with user-defined goals (e.g., maximize profit or volume).
- Support multi-brand optimization without interdependency between SKUs and brands.
- Collaborate with cross-functional teams to validate model behavior and outcomes.
Inputs You'll Work With
- SKU-level data: volume, elasticity, profitability, TDP, and price bounds.
- Business rules: brand-level caps, SKU exclusions, optimization targets.
Deliverables
- Modular Python-based optimization engine.
- JSON-based input/output support for seamless integration.
- Logging and fallback mechanisms for infeasible constraints.
- Unit tests and validation with historical data.
Tech Stack & Skills
- Proficient in Python, especially NumPy, Pandas, SciPy or Pyomo/CVXOPT.
- Experience with constrained optimization techniques.
- (Preferred) Background in price optimization, demand modeling, or econometrics.
Skills Required
Python, Numpy, Pandas, Scipy