• Develop OR-based models for fulfillment routing, labor scheduling, and queuing, triaging & agent optimization. • Apply techniques such as mixed-integer programming, dynamic programming, graph theory, spatial optimization and simulation to solve real-time decisioning problems. • Integrate predictive ML models with optimization logic to enable adaptive, data-driven decisions. • Build and operationalize decision engines that automate fulfillment decisions across the enterprise. • Collaborate with engineering to deploy models into production systems with real-time data pipelines and monitoring. • Ensure models are interpretable, auditable, and aligned with business constraints. • Combine ML outputs with OR solvers via hybrid decision frameworks, enabling scenario-aware optimization and policy simulation. • Ensure robustness and scalability of models by leveraging containerized environments and observability tools. • Enable real time decisioning by building & incorporating streaming pipelines and supporting low latency inference and optimization. • Use graph-based models and reinforcement learning to dynamically adjust pick paths and task sequences. • Partner with product and operations to define decision boundaries, constraints, and success metrics. • Communicate insights and model performance to technical and nontechnical audiences. • Understand latest research in the field of OR and AI to give inputs to enterprise roadmaps to ensure we are on the path to build Best in Class fulfillment and athlete service solution.