In this paper, a new robust nonlinear observer is proposed for the reconstruction of the whole process state variables in a simulated polymerization reactor. It presents an interconnected high gain observer to perform the estimation. This observer has robust performance in the presence of measurement noise and model uncertainty. The global stability of the observer is analytically treated using the Lyapunov theory in order to show the conditions under which exponential convergence can be achieved. Finally, we present a numerical simulation to illustrate the effectiveness of the suggested approach.