The intersection of medicine and engineering holds significant promise for advancing cancer treatment. Traditional chemotherapy, which typically employs maximum tolerable doses, often leads to severe side effects and the development of drug resistance. This study presents a novel approach to optimize chemotherapy treatment plans using a genetic algorithm, enabling personalized therapy tailored to individual patient parameters derived from in vivo experimental data. The proposed method aims to reduce tumor size while minimizing drug dosages, thereby decreasing treatment costs and toxicity. To get more accurate results, we define basis functions based on real-world treatment protocols and use them as building blocks for the optimized therapy. Our approach was first tested on individual patients and then extended to a set of patients with similar parameters. The results demonstrate that the generated treatments significantly improved survival rates with only a moderate increase in drug doses compared to standard clinical treatments. These findings suggest that personalized chemotherapy, facilitated by advanced computational techniques, can offer more effective and patient-friendly cancer care. Future research will focus on refining the algorithm and conducting clinical trials to further validate this promising approach.