This study aimed to investigate the incidence of subclinical mastitis (SCM), the implicated pathogens, and their impact on milk quality in dairy sheep in Greece. Furthermore, we preliminarily evaluated infrared thermography and the application of AI tools for the early, non-invasive diagnosis of relevant cases. In total, 660 milk samples and over 2000 infrared thermography images were obtained from 330 phenotypically healthy ewes. Microbiological investigations, a somatic cell count (SCC), and milk chemical analyses were performed. Infrared images were analyzed using the FLIR Research Studio software (version 3.0.1). The You Only Look Once version 8 (YOLOv8) algorithm was employed for the automatic detection of the udder’s region of interest. A total of 157 mammary glands with SCM were identified in 122/330 ewes (37.0%). The most prevalent pathogen was staphylococci (136/160, 86.6%). Considerable resistance was detected to tetracycline (29.7%), ampicillin (28.6%), and sulfamethoxazole–trimethoprim (23.6%). SCM correlated with high total mesophilic count (TMC) values and decreased milk fat, lactose, and protein content. A statistically significant variation (p < 0.001) was identified in the unilateral SCM cases by evaluating the mean temperatures of the udder region between the teats in the thermal images. Finally, the YOLOv8 algorithm was employed for the automatic detection of the udder’s region of interest (ROI), achieving 84% accuracy in defining the ROI in this preliminary evaluation. This demonstrates the potential of infrared thermography combined with AI tools for the diagnosis of ovine SCM. Nonetheless, more extensive sampling is essential to optimize this diagnostic approach.