Electromobility is emerging as a pivotal component of the energy transition, contributing significantly to the reduction of CO2 emissions in the transport sector. The increasing penetration of electric vehicles, however, presents substantial challenges for energy system management and grid infrastructure. A critical issue is the reliance on conventional household standard load profiles to approximate the demand of Electric Vehicle (EV) charging stations. These profiles fail to represent the distinctive characteristics of charging behavior, resulting in pronounced deviations from actual demand and creating potential threats to grid stability. Accurately modeling charging station load profiles is therefore essential for assessing system impacts and developing effective stabilization strategies. The objective of this work is to develop a model for generating parameterizable load profiles specifically designed for electric vehicle charging stations, consistent with the framework established by Bundesverband der Energie- und Wasserwirtschaft e.V (BDEW). Unlike traditional approaches, the proposed parameterizable profiles incorporate both temporal influences (e.g., time of day, day of week, season) and contextual metadata (e.g., location, connected load). To enhance predictive capability, artificial intelligence techniques are employed to identify and integrate novel parameters that influence charging behavior. The anticipated contribution of the study is the provision of flexible, data-driven load profiles that substantially reduce deviations from real-world charging data. These refined profiles are expected to support grid operators and policymakers by improving system planning, facilitating the integration of charging stations into existing infrastructure, and ultimately contributing to long-term grid stability.