Electric Vehicles (EVs) are being increasingly used in the transportation domain due to recent advancements in the field of energy systems. As such, there is an increased need for intelligent and sustainable EV charging infrastructure for large-scale EV integration to minimize the impact on the grid. Renewable-powered Community EV Charging Stations (CECSs) have emerged as a possible option to solve this problem, but their usage is hindered by the challenges associated with renewable power sources, stochasticity in the demand for EV charging services, and the possibility of charging congestion. In order to overcome these challenges, this paper proposes an energy management hierarchy that utilizes fuzzy Q-learning reinforcement learning (FQ-RL) coupled with Stackelberg game-theoretic optimization for efficient and personalized EV charging management. In the upper layer of decision-making, the FQ-RL decides on the charging tariff based on information from the real-time operation of the system, such as SPV power generation, state of charge (SoC) of the battery, and occupancy in the EV queue. In the lower decision layer, the Stackelberg game approach is used to model the interaction between the charging station provider and the EV drivers to make coordinated charging decisions via dynamic pricing considering their preferences and flexibility. The framework improves the interaction between the CECS and the utility grid through higher usage of renewables, reduced grid reliance, charging station congestion avoidance, and profitability of charging stations. Compared with the flat-rate tariff baseline, the proposed FQ–RL–Stackelberg framework using the AHP-selected balanced configuration achieved a 30.12% increase in delivered charging energy, a 13.57% reduction in peak grid demand, and an 83.33% reduction in unserved EVs. These results demonstrate the potential of intelligent charging strategies for developing sustainable, user-centric, and renewable-integrated EV charging infrastructure that supports future smart grids and intelligent transportation systems.