System reliability optimization models containing uncertainty are expressed and a new formulation is proposed to maximize the reliability subject to the available cost of the system reliability estimate. The redundancy allocation problem can be defined as the selection of the system configuration and the type of the components to optimize some objective functions while satisfying some system related constraints. This paper proposes a solution for multistage series-parallel system with nonlinear function to evaluate the maximum reliability subject to available cost using triangular intuitionistic fuzzy number. In addition to that, we propose the coefficient of variance of the system reliability estimate for each membership function and non-membership function. These methods are utilized to identify minimum CV with high reliability estimate. © 2015 Pushpa Publishing House, Allahabad, India