Organic Rankine Cycles (ORCs) generate power from low temperature heat. To make the best use of the diverse low temperature heat sources, the cycle is tailored to each application. The objective is to maximize process performance by optimizing both process parameters and the working fluid. Today, process optimization and working fluid selection are typically addressed separately in a two-step approach: working fluids are selected using heuristic knowledge; subsequently, the process is optimized. Such an approach can lead to suboptimal solutions, since the optimal fluid might be excluded by the heuristics. We therefore present a framework for the holistic design of ORCs enabling the simultaneous optimization of the process and the working fluid based on process performance. The simultaneous optimization is achieved by exploiting the rich molecular picture underlying the PC-SAFT equation of state in a continuous-molecular targeting approach (CoMT-CAMD). To allow for the prediction of caloric properties, a quantitative structure property relationship (QSPR) for the ideal gas heat capacity is proposed that relies on pure component parameters of PC-SAFT. The framework is used for the optimization of a geothermal ORC in a case study. A sound holistic design of process and working fluid is achieved.