In this paper, a stochastic programming framework is presented to address process synthesis problems under uncertainty. The framework is based on a two-stage stochastic MINLP formulation for the maximization of a function comprising the expected value of the profit, operating and fixed costs of the plant. Three alternative integration schemes are proposed for the evaluation of the expectancy, and their computational performance is studied through general synthesis problems. Results from different implementations on advance computer architectures are also reported to analyze the parallelization of the algorithm. The effects of the number of integration points, the size of the problem, and the number of uncertain parameters on the computational performance are also discussed.