Abstract The purpose of the present paper is to propose a methodology for the fluid selection of an Organic Rankine Cycle for low-temperature waste heat recovery. The selection of an optimal working fluid is carried out by an optimization process, using the Genetic Algorithm. Three decision variables are considered: the working fluid, the evaporation temperature and the condensation temperature. These variables are subjected to some constraints that take into account the good operation of the heat exchangers and the expander. The defect of efficiency and the total heat exchange area per unit of power output are selected as the objective functions to be minimized. The heat recovery is made possible by a hot water source, which assumes inlet temperatures of 100 °C and 150 °C. The water mass flow rate is fixed to 1.0 kg/s. The results show that fluids with low value of critical temperature, like Novec649, RE347mcc, R245fa, optimize the defect of efficiency, whilst, in order to minimize the total heat exchange area per unit of power output, fluids with high value of thermal conductivity and latent heat of vaporization must be selected. This work offers a tool to selected an optimal working fluid, among all possible candidates, for this type of applications.