Bayesian updating is used to approximate discontinuous multi-interval uncertainty representations (i.e., belief structures) of epistemic uncertainty. Several Bayesian-based approaches are examined for assessing the accuracy of approximating the mean and standard deviation of a belief structure and calculating reliability using posterior distributions. Moreover, a Bayesian-based belief structure approximation is integrated with a decomposed multilevel optimization solution strategy through analytical target cascading, where the ensuing reliability-based design optimization problem within each decomposed element is solved using a single loop single vector approach. The non-deterministic decomposed multilevel optimization approach is demonstrated through solutions to four analytical benchmark problems with mixed aleatory and epistemic uncertainties as well as a nano-enhanced composite sandwich plate problem. Consistent with the integrated computational materials engineering philosophy, the proposed solution strategy for the sandwich plate problem combines micro- and macro-level material modeling and design with structural level analysis and optimization. The orientation distribution of the carbon nanofibers in the micro-mechanical model is described through a belief structure and modeled using a Bayesian approach. Aleatory uncertainty in the ply thickness of the composite facesheets is also considered. This problem is used to demonstrate computationally efficient integration of epistemic uncertainty described through a belief structure for a complex design problem with mixed uncertainties. The results of this study show that the posterior distributions from some of the Bayesian-based approaches are suitable for direct calculation of reliability through joint probability density functions. Moreover, the Bayesian-based approach can provide a computationally efficient method for integrating epistemic and aleatory uncertainties in decomposed multilevel optimization of complex problems.