This paper presents an experimental application of parameter estimation and PI controller design for a state-coupled two-tank liquid level system. For this plant it is desired to provide a satisfactory performance for the control system. In the proposed approach a genetic algorithm optimization method is used to estimate the plant physical parameter values of the nonlinear system. The GA has been provided the system parameters as well as the real system performance is achieved. Then, a proportional-integral controller is designed to control the plant based on the linearized model and implemented experimentally. The experimental implementation provides a good performance and response.