This paper presents a novel and systematic optimization approach to design a robust controller for single-input/single-output process systems in the presence of unknown but bounded parameter uncertainties. The main idea is that of transforming the robust controller design problem into a nonlinear programming problem (NLP) through using the well-known Kharitonov and Hermite-Biehler stability theorems. For illustration, the proposed approach is applied to design a robust proportional-integral controller for a recycle system in the presence of process gain uncertainties.