Expertise in designing and orchestrating multi-agent architectures powered by LLMs like GPT, leveraging AutoGen and Langfuse frameworks to enhance intent classification and multi-agent collaboration.Driving the implementation of high-performance AI solutions, including prompt engineering and agent metadata management, for seamless agent-based conversations and customer interactions.Developing and optimizing AI-based systems for real-time intent routing, integrating LLMs for contextual decision-making across multiple business use cases.Leading cloud-native AI solutions with a focus on multi-cloud deployment, ensuring high availability and scalability for AI systems in production.Extensive experience with DevOps, microservice architectures, and CI/CD pipelines, ensuring smooth integration of AI-driven systems into existing enterprise platforms.Experience in LLM performance evaluation, latency analysis, and prompt optimization for specific tasks.