Sustainability presents significant challenges in supply chain management, particularly in managing production waste, which often leads to high storage and disposal costs while contributing to environmental degradation. During manufacturing processes, raw materials utilization has to be optimized through the well-structured management of waste to increase the company's sustainable performance. Indeed, industry 5.0 concepts such as artificial intelligence contribute to this improvement. This paper, focusing on metaheuristic algorithms, recognized for their efficiency in solving complex optimization problems, addresses these issues by rapidly providing near-optimal solutions. Specifically, a genetic algorithm is used to tackle a two-dimensional cutting stock problem, aiming to reduce material waste while studying the environmental impact and minimizing associated costs, such as greenhouse gas emissions per unit of material, transportation and waste costs. To broaden the model’s scope and relevance, critical supply chain aspects, including inventory management, are incorporated. This integration ensures a holistic approach to improving sustainability and operational efficiency. The framework’s effectiveness is demonstrated through its application to a real-world case study, showcasing its potential to address both environmental and economic objectives. The results underline the practicality and value of using advanced optimization techniques in developing sustainable and cost-efficient supply chain strategies.