Hybrid electric vehicles (HEV) are essential for reducing fuel consumption and emissions. In many cases, the same type of electrified powertrains is used for many different tasks and applications. However, when analyzing different segments of the transportation industry, for example, public transportation or different sizes of delivery trucks and how the HEV are used, it is clear that one powertrain is not optimal in all situations. Choosing a hybrid powertrain architecture and proper component sizes is an important task to find the optimal trade-off between fuel economy, drivability, and vehicle cost. However, exploring and evaluating all possible architectures and component sizes is a time-consuming task, both because evaluating the performance of each architecture is computationally costly and because the design search space grows exponentially with the number of components to be optimized. A search algorithm, using Gaussian Processes, is proposed that explores multiple architecture options, to identify the Pareto-optimal solutions. The search algorithm is designed to carefully select the candidate in each iteration which is most likely to be Pareto-optimal, based on the results from previous candidates, to reduce computational time. The powertrain is optimized for a medium-sized series plugin hybrid electric delivery truck with a range extender. Different powertrain architectures are included in the design space exploration and the fuel economy is evaluated using a simulation model of the powertrain and Dynamic Programming. The powertrain is optimized for three different driving missions in the analysis, represented by different driving cycles, and the results are evaluated.