This study presents the Reliability Based Design Optimization (RBDO) of a helicopter, used in order to guarantee target performances for a large variation of annual atmospheric temperatures. To this end, analytic methods - statistical and empirical equations of aerodynamics, structure, propulsion and so on - are synthetically coupled within the multidisciplinary design analysis tool of the conceptual helicopter. Additionally, an atmospheric temperature model for annual air temperature variation is constructed in bimodal shape by considering 10 years worth of day-averaged air temperature data provided by the Korea Meteorological Administration. Based on this analysis tool and the annual atmospheric temperature model, the RBDO of a helicopter is performed to minimize maximum takeoff gross weight, with the helicopter rotor configuration parameters as a design variable. A Monte-Carlo simulation is used to accurately evaluate the reliabilities of endurance and range. This RBDO strategy is applied to a 22,000lb class medium utility helicopter, and the results are compared with those of a deterministic design optimization (DO) using constant air temperature and baseline helicopter. Through comparison of the results obtained from RBDO and those from the deterministic design optimization, it can be continued that the optimal design of RBDO results in greater improvements in performance over the baseline, for a wide range of operating air temperatures, than baseline helicopter and optimal shape of DO using constant air temperature. Therefore, in designing a helicopter to be operated in temperate climatic regions that show large variation in air temperature, such as Korea, China, the U.S.A, and so on, it is important to perform RBDO with reasonable annual air temperature models constructed from well-known and reliable data.