I am an AI Engineer with hands-on experience designing and deploying end-to-end AI systems in production environments. My work primarily revolves around building scalable Retrieval-Augmented Generation (RAG) systems and Natural Language-to-SQL solutions that enable intuitive interaction with large-scale data. I have strong experience integrating large language models with external APIs and backend services, ensuring seamless communication across systems. I regularly work with cloud platforms such as AWS and GCP to deploy, monitor, and scale applications, leveraging tools for data pipelines, model hosting, and infrastructure management. My expertise includes LLMs, vector databases, prompt engineering, and optimizing systems for performance, latency, and cost. I also emphasize software engineering best practices, including clean architecture, CI/CD pipelines, and system monitoring, to build robust and maintainable AI solutions.