The design of an optimal supply chain rarely considers uncertainty within the modeling framework. This omission is due to several factors, including tradition, model size, and the difficulty in measuring the stochastic parameters. We show that a stochastic program provides an ideal framework for optimizing a large supply chain in the face of an uncertain future. The goal is to reduce disruptions and to minimize expected costs under a set of plausible scenarios. We illustrate the methodology with a global production problem possessing currency movements.