Continuous monitoring of nocturnal blood pressure is crucial for hypertension management and cardiovascular risk assessment. However, current clinical methods are invasive and discomforting, posing challenges. These traditional techniques often disrupt sleep, impacting patient compliance and measurement accuracy. Our research introduces a groundbreaking, non-contact system for continuous monitoring of nocturnal blood pressure, utilizing ballistocardiogram (BCG) signals. The key component of this system is the utilization of advanced, flexible fiber optic sensors designed to accurately capture medical-grade BCG signals. Our artificial intelligence (AI) model extracts deep learning and fiducial features with physical significance and implements an efficient, lightweight personalization scheme on the edge device. Furthermore, the system incorporates a crucial algorithm to automatically detect the user's sleeping posture, ensuring accurate measurement of nocturnal blood pressure. The model underwent rigorous evaluation using open-source and self-collected datasets comprising 158 subjects, demonstrating its effectiveness across various blood pressure ranges, demographic groups, and sleep states. This innovative system, suitable for real-world unconstrained sleeping scenarios, paves the way for enhanced hypertension screening and management, as well as opening new avenues for clinical research into cardiovascular complications.