AI/ML Engineer (Generative AI) with 2.5+ years of production experience building LLM-powered systems, Retrieval-Augmented Generation (RAG) pipelines, prompt engineering, agent-based automation, and Agent-to-Agent (A2A) communication frameworks in the telecom domain. Hands-on with Python, PyTorch, TensorFlow, Keras, FastAPI, LangChain, vector databases & embeddings, and MCP-enabled AI services on AWS and Azure. Experienced in model training, fine-tuning, and evaluation, data preprocessing, MLOps / CI-CD pipelines, and model monitoring. Proven record of reducing engineer query resolution time by 60%, cutting API costs by 40%, and achieving 99.5% uptime on cloud-deployed GenAI microservices across AWS Bedrock and Azure OpenAI.