Optimisation under uncertainty is an important task for practitioners of engineering design optimisation since industrial applications are often affected by uncertainties such as unknown or variable environmental conditions, variability in material or geometrical properties and model assumptions. Optimisation under uncertainty presents several challenges, such as, the proper treatment of uncertainties of various natures (probabilistic or epistemic), the quantification of the impact of uncertain input variables on system responses and the proper way to deal with large-scale problems. At the foundation of optimisation under uncertainty is uncertainty quantification often referred to as UQ . Due to the input stochasticity, system responses are also stochastic, but their statistical properties are not known a priori. UQ aims at determining them as precisely as possible and the best approach may lie in incorporating UQ directly into the engineering design optimisation process, when it is affordable in terms of computational costs.