By combining agricultural output with solar energy production, agri-photovoltaic (Agri-PV) systems provide a long-term answer to land-use issues. To maximize energy production and crop yield, however, one must strike a balance between available light and shade. In order to find the optimal tilt angle and row spacing of PV panels in Agri-PV systems, this paper suggests an optimization framework based on Genetic Algorithms (GA). Combining state-of-the-art crop yield modeling with real-world irradiance and yield data from experimental field research, the model takes into consideration weather, soil, and plant physiology. The trade-offs between energy generation and agricultural yield are investigated using a multi-objective optimization technique that employs Pareto front analysis. When compared to Particle Swarm Optimization (PSO) and Teaching-Learning-Based Optimization (TLBO), the GA framework clearly performs better. Additionally, the suggested system's viability and adaptability have been validated by an economic and scalability study. The simulation findings show that GA is a great tool for optimizing Agri-PV schemes in different agro-climatic zones.