The study of underwater environments has been revolutionized by the use of autonomous underwater vehicles. However, effective guidance and control of these vehicles face challenges such as modeling errors, environmental disturbances, and the inherent under-actuation of many designs. To address these challenges, we propose a Neuro-Adaptive Fixed-Time Sliding Mode Control framework for under-actuated underwater vehicles. The issue of under-actuation is resolved using a line-of-sight guidance system based on look-ahead distance, enabling accurate trajectory tracking. A Fixed-Time Sliding Mode Controller is employed to guarantee faster convergence. To handle modeling uncertainties, the controller is augmented with a neural network (NN) trained using a composite error learning, which incorporates prediction errors from a state observer into the NN weight update law, enhancing learning performance. Additionally, a Disturbance Observer (DOB) is integrated to estimate and counteract environmental disturbances. The stability of the proposed control system is proven using Lyapunov theory. To validate its effectiveness, the control framework is tested in a high-fidelity simulation under scenarios involving significant uncertainties, external disturbances, and actuator faults.