<p>In recent years, the incorporation of renewable energy sources (RESs), particularly photovoltaic (PV) systems, with electric vehicle (EV) system configuration has garnered momentous attention owing to its ability to improve reduce carbon emissions and sustainability. Efficient power management techniques, such as maximum power point tracking (MPPT), are crucial for maximizing energy extraction from PV arrays, thereby optimizing the performance of PV-based EV systems. This paper proposes an innovative approach by combining an improved bacterial foraging optimization technique with radial basis function neural network (IBRBFNN)-based MPPT algorithm tailored for a coupled inductor K S Kavin (CI-KSK) converter to charge the EV load. By regulating the timing and duty cycle of the switching operation, the CI-KSK converter has the ability to govern the output voltage to the desired level. This control mechanism ensures that the converter operates efficiently and effectively boosts the PV voltage to match the requirements of the EV load. Besides, the proposed converter affords minimized leakage reactance, high voltage conversion efficiency, and minimal energy losses during the conversion process. The proposed optimized MPPT algorithm efficaciously handles the nonlinearities in the PV system, enabling precise tracking of the MPP under varying environmental circumstances. An extensive simulation is conducted in MATLAB simulation platform to substantiate the effectiveness of the developed system. The attained findings demonstrate that the CI-KSK converter with improved BF-optimized RBFNN-based MPPT algorithm outperforms traditional approaches with regard to efficiency, convergence speed, and robustness. The MPPT controller achieves higher tracking efficiency, leading to increased energy harvesting from the PV system and improved performance for the EV with maximum efficiency value of 97.2%.</p>