Published Paper Details:

The demand for generative AI (GAI) applications grows, and scalable architectures in cloud computing environments become imperative to support such models' computational complexity and resource demands. In this paper, we dive deep into scalable architectures for generative AI in the cloud, aiming to boost performance and efficiency. Distributed computing, containerization, and edge computing are some architectural approaches we explore to allow organizations to surmount the resource requirements of GAI models. We explore how scalable infrastructure, smart resource management, and data management practices are used in combination for the deployment and execution of GAI applications through case studies and performance benchmarks. The results show the pros and cons of each architectural framework and outline future directions for integrating emerging technologies, such as quantum computing and serverless architectures, for increased scalability. This research applies to practical applications across various industries, from healthcare to finance and entertainment to increasing the employment of GAI applications to drive innovation and efficiency.