With progress of space technology and increase of space mission demand, requirements for robustness and reliability of space systems are ever-increasing. For the whole space mission life cycle, the most important decisions are made in the conceptual design phase, so it is very crucial to take uncertainties into consideration in this initial phase to assure a feasible, reliable and robust conceptual design baseline which dominates the later design direction and life cycle cost. To enhance space system design quality in the conceptual design phase, the utilization of Uncertainty Multidisciplinary Design Optimization (UMDO) in the systems engineering process is systematically studied in this paper. The UMDO theory is introduced and its application in space system design is studied considering the complexity of the system. A small satellite system design case is further discussed to demonstrate the efficacy of UMDO in improving the space system design.