Organic semiconductors (OSCs) are essential not only for next generation optoelectronics but also for clean energy (e.g., organic solar cells), flexible electronics, and sustainable technologies due to their low cost, lightweight, and tunable properties. However, the vast chemical space of OSCs makes traditional trial and error discovery slow and resource intensive. Quantum chemical methods are accurate but computationally expensive for large scale screening. Recent advances in machine learning (ML) and deep learning (DL) offer a powerful alternative. By combining high throughput computational screening with ML/DL, we can rapidly predict the structures and properties of thousands of OSC candidates, dramatically accelerating the design cycle toward greener and more efficient materials. This summer project invites undergraduates to build predictive AI models to explore how AI can drive innovation in energy and electronics, bridging traditional chemistry with modern data driven approaches for a sustainable future.