This article examines the application of electrorheological (ER) lubricant in hybrid thrust bearings. ER lubricant is composed of dielectric micro-particles suspended in insulating silicon oil, and the electrorheological effect significantly boosts the performance of mechanical components like bearings. The study solves the modified Reynold's equation using Finite Element Analysis and applies a mass-conserving Jakobsson-Floberg-Olsson (JFO) algorithm to the textured surface area. By introducing micro-textures, a hydrostatic thrust bearing is converted into a hybrid thrust bearing. While surface texturing has been extensively researched, its industrial adoption remains difficult. Improperly optimized texture geometry can negatively affect bearing performance, leading to undesirable outcomes. Given the significant role surface texture plays in hybrid thrust bearing performance, optimizing texture characteristics is vital for achieving optimal results. This study investigates the impact of surface texturing on the thrust pad when using ER lubricant and employs an Artificial Neural Network (ANN) approach to optimize texture parameters. By leveraging artificial intelligence, the model encourages both researchers and industrial manufacturers to integrate surface texturing into their processes. The study demonstrates that the Genetic Algorithm (GA) outperforms the Teaching-Learning-Based Optimization (TLBO) method, with the optimal texture parameters being a width of 7.9544, a length of 0.4010, and a depth of 1.0745. These optimal texture parameters lead to significant improvements in the steady-state and dynamic performance indices of the bearing system.