The realization of lightweight and high-performance materials is essential for advancing electric vehicle (EV) technologies. A fundamentally new computational modeling framework for design and optimizing the rolling process of the AZ61 magnesium alloy containing (6 wt.% aluminium, and 1 wt.% zinc) composite providing an ideal combination of high strength and ductility for EV applications. Based on artificial neural network (ANN), the research uses an approximation model of non-linear and coupled thermal–mechanical interactions in the rolling process. Modeling of key process parameters such as rolling temperature, number of passes, and initial thickness, where the mechanical properties such as tensile strength and ductility were predicted. The novelty of this work is the use of ANN to both empower a comprehensive exploration of the nontrivial parameter-property space as well as an optimization that are often difficult to achieve with classical means. This new AZ61 composite presents enhanced mechanical properties, crucial for lightweight EV components, thus resulting in enhanced energy efficiency without compromising on the structural integrity. This computational approach paves the way for more scalable methodologies to design lightweight materials and cut down trial-and-error experiments in industrial practices. Blueprints for the optimized magnesium alloys will serve as a springboard for future implementations of AI to design new materials with improved properties, accelerating progress in EV materials design and fabrication methods.