Principal Scientist

Key Responsibilities

• Design and deploy Multi-Agent Reinforcement Learning (MARL) systems for pricing optimization across product categories, competitive dynamics, and demand scenarios
• Develop promotional strategies using optimization algorithms to maximize revenue, margin, and market share while maintaining price elasticity
• Analyze retail pricing data, consumer behavior patterns, and competitive intelligence to identify optimization opportunities
• Build simulation environments for testing pricing scenarios before production deployment
• Collaborate with data science teams to integrate RL models into pricing decision workflows
• Create dashboards and reports demonstrating pricing strategy impact on KPIs
• Work directly with retail merchandising and revenue teams to align AI-driven recommendations with business objectives

Required Qualifications

• 6-10years of experience in pricing/promotions roles within retail store-based companies (grocery, consumer goods, or fashion retail preferred)
• Strong foundation in Reinforcement Learning, particularly Multi-Agent RL, Q-Learning, or Policy Gradient methods
• Proven experience with optimization techniques (linear programming, constrained optimization, dynamic programming)
• Hands-on expertise in Python with libraries like Ray RLlib, Stable Baselines3, or similar RL frameworks
• Deep understanding of retail pricing mechanics, promotional calendars, and markdown strategies
• Experience with price elasticity modeling and demand forecasting

Preferred Qualifications

• Master's degree in Operations Research, Computer Science, Economics, or related quantitative field
• Experience deploying RL models in production retail environments
• Knowledge of A/B testing methodologies for pricing experiments
• Familiarity with retail POS systems and pricing management platforms