Ranjit K.

 I am an AI/ML Engineer specializing in Generative AI and large language model (LLM) applications. I have hands-on experience building production-grade RAG pipelines using LangChain, OpenAI embeddings, and vector databases like Pinecone. I have designed scalable document ingestion systems using AWS Lambda and event-driven architectures. My focus is on building cost-efficient, low-latency AI systems with proper retrieval, re-ranking, and MLOps practices. I am passionate about solving real-world problems using AI and continuously improving system performance, scalability, and reliability.