Hi, I’m Pooja Prabhakar, an AI/ML Engineer specializing in Retrieval-Augmented Generation (RAG) and large language model applications. Over 3+ years at AWS, I’ve designed and deployed production-grade RAG knowledge bases using LangChain, LlamaIndex, FAISS, ChromaDB, and AWS OpenSearch to accelerate annotation lookup and improve retrieval efficiency. I’m proficient in Python, vector databases, embedding generation, and prompt engineering; I’ve built embedding workflows, chunking strategies, and prompt libraries for high-quality LLM outputs. I’m AWS-certified and actively building a full-stack AI/ML engineering portfolio, with a focus on LangChain and LlamaIndex. I’m currently contributing to ML Data Ops and ML Data pipelines at AWS, leading RAG and vector database integration, embedding workflows, and quality assurance. I collaborate with cross-functional teams on fine-tuning, transfer learning, and responsible AI data initiatives, and I mentor teams in data standardization and SOP development.…Hi, I’m Pooja Prabhakar, an AI/ML Engineer specializing in Retrieval-Augmented Generation (RAG) and large language model applications. Over 3+ years at AWS, I’ve designed and deployed production-grade RAG knowledge bases using LangChain, LlamaIndex, FAISS, ChromaDB, and AWS OpenSearch to accelerate annotation lookup and improve retrieval efficiency. I’m proficient in Python, vector databases, embedding generation, and prompt engineering; I’ve built embedding workflows, chunking strategies, and prompt libraries for high-quality LLM outputs. I’m AWS-certified and actively building a full-stack AI/ML engineering portfolio, with a focus on LangChain and LlamaIndex. I’m currently contributing to ML Data Ops and ML Data pipelines at AWS, leading RAG and vector database integration, embedding workflows, and quality assurance. I collaborate with cross-functional teams on fine-tuning, transfer learning, and responsible AI data initiatives, and I mentor teams in data standardization and SOP development.WWWW…