In today's complex and uncertain global landscape, supply chain disruptions pose significant challenges to businesses. This study presents an AI-enabled risk management framework that integrates mathematical modeling and metaheuristic optimization to enhance supply chain resilience. A multi-objective optimization model is developed to minimize total costs while mitigating risks associated with supplier reliability, transportation uncertainties, and disruption scenarios. The study employs three advanced optimization algorithms: Genetic Algorithm (GA), Non-Dominated Sorting Genetic Algorithm II (NSGAII), and the recently developed Greedy Man Optimization Algorithm (GMOA). Comparative analysis reveals that GMOA outperforms traditional algorithms in achieving near-optimal solutions with faster convergence. Sensitivity analysis further highlights the critical impact of AI-driven decision-making on risk mitigation. This research provides valuable insights for supply chain managers and policymakers, emphasizing the role of AI-driven optimization in ensuring sustainable and adaptive supply chains.