 This paper proposes a cloud-based AI-enhanced framework to estimate the state of charge, SOC, and state of health, SOH, of rechargeable lithium-ion batteries over their operational lifetime. The framework leverages self-supervised transformer neural networks to capture the long-term behavior of the system and its components. By coupling the cloud-edge computing architecture with the versatility of deep learning, the proposed framework can take advantage of the predictive capabilities of exploiting long-range spatial-temporal dependencies across multiple scales. This approach has the potential to provide accurate predictions of the battery's performance and enable more efficient operation of EVs. This article was authored by Depaichur, Jingyuan Zhao, Jinghong Wang, and others.