Cloud manufacturing (CMfg), as a new service-oriented technology, is aiming towards delivering on-demand manufacturing services over the internet by facilitating collaboration among different producers with distributed manufacturing resources and capabilities. To this end, addressing service composition and optimal selection (SCOS) problem has been the pivotal challenge. This NP-hard combinatorial problem deals with selecting and combining the available resources into a composite service to meet the user’s requirements while keeping up the optimal quality of service. This study proposes a new hybrid approach based on the recently developed grey wolf optimizer (GWO) algorithm and evolutionary operators of the genetic algorithm. The embedded crossover and mutation operators carry out a twofold functionality: (1) they make it possible to adapt the continuous structure of GWO to a combinatorial problem such as SCOS, and (2) they help to avoid the local optimal stagnation at the hunting process by providing more exploration strength. A series of experiments were designed and conducted to prove the effectiveness of the proposed algorithm, and the experimental results demonstrated that the proposed algorithm delivers superior performance compared with that of both existing discrete variations of GWO and genetic algorithm, especially in large-scale SCOS problems.