Recent advancements in Bayesian inference for pulsar timing array (PTA) data analysis have focused on enhancing both efficiency and accuracy through the application of normalizing flow-based nested sampling techniques. The study integrates the i-nessai sampler, which leverages importance nested sampling with normalizing flows, within the widely used Enterprise framework for PTA analysis. This integration aims to streamline the inference process by better capturing complex posterior distributions inherent in PTA datasets. The effectiveness of this approach has been demonstrated on simulated datasets, showcasing improvements over traditional sampling methods. These developments represent a significant step forward in the analysis of PTA data, potentially enabling more precise gravitational wave detection efforts. The work aligns with ongoing research trends emphasizing the use of advanced machine learning tools to refine astrophysical data interpretation. This progress is contextualized within a broader movement toward leveraging normalizing flows in Bayesian inference, as noted in recent related studies.