While artificial Intelligence (AI) transforms recruitment by allowing organisations to employ data-driven hiring decisions, it is prone to reinforcing biases, posing ethical and fairness concerns. This study introduces HITHIRE, an AI-driven recruitment model designed to enhance transparency, fairness, and inclusivity within the diverse workforce of Saudi Arabia. A baseline model was first evaluated using Llama 3.1, BERT (Bidirectional Encoder Representations from Transformers), and Regular Natural Language Processing (NLP) techniques. However, it revealed significant biases in gender and nationality-based hiring. The Llama 3.1 model was enhanced through data augmentation, sentence transformers, standard scoring, and transparency mechanisms, resulting in the HITHIRE model. Fairness analysis indicated measurable improvements across gender, nationality, and intersections, with reduced Statistical Parity Difference (SPD) and Disparate Impact (DI) scores. For gender, SPD was reduced to 0.0156 and DI improved to 0.978 (from baseline values of 0.0847 and 1.1892, respectively). At the same time, the nationality-based Theil Index dropped to 0.3747 from 0.6721, indicating enhanced equity across diverse groups. It also achieved a perfect Average Odds Difference (AOD) and Equal Opportunity Difference (EOD) values of 0.0000. Further, HITHIRE also achieved a Precision of 0.93, a Recall of 1.0, an F1 Score of 0.96, and an ROC AUC of 0.95. The findings highlight the potential of ethical AI integration in recruitment, ensuring unbiased, accountable, and transparent hiring practices. While BERT, Llama 3.1, and transformers are well-established, HITHIRE is one of the first LLM adaptations explicitly fine-tuned for the Saudi Arabian hiring context, combining accuracy and fairness with cultural alignment. This is critical in ethical AI deployment in non-Western hiring systems, adding to the global fairness discourse in global human resource policies.