This work presents the design, modeling, and simulation of an intelligent solar photovoltaic (PV)-powered electric vehicle (EV) charging station integrating advanced power management and energy management strategies. The system incorporates an ANFIS-based maximum power point tracking (MPPT) controller to extract optimal PV power under varying irradiance conditions, a stationary battery and EV battery interfaced through bidirectional DC–DC converters, and a single-phase grid-connected inverter equipped with an LCL filter. A neural network-based energy management system (EMS) generates dynamic current reference signals for the inverter based on real-time PV power and battery state of charge (SOC), enabling intelligent allocation of energy between PV, stationary storage, EV battery, and the grid. The model is implemented in MATLAB/Simulink, and three scenarios are analyzed based on different SOC levels of stationary and EV batteries. Results demonstrate that ANFIS MPPT achieves fast and accurate tracking of maximum PV power, while the neural network EMS ensures smooth power flow transitions between grid import, grid export, and hybrid operating modes. The DC bus voltage remains regulated at 500 V throughout all test conditions, and the EV battery consistently charges even under low irradiance. The proposed system confirms enhanced stability, flexibility, and renewable utilization compared to conventional rule-based or PI-only methods. The study highlights the potential of combining AI-based MPPT and neural network EMS for next-generation smart EV charging infrastructure.