• Work with LLMs such as GPT, Llama, Gemini, and other open-source or commercial models. • Develop and optimize prompts to improve model accuracy and response quality. • Build Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models. • Implement NLP techniques for text processing, summarization, classification, and information extraction. • Integrate LLMs with applications using APIs and frameworks such as LangChain or LlamaIndex. • Work with vector databases such as FAISS, Pinecone, Chroma, or Weaviate. • Evaluate model performance, reduce hallucinations, and optimize response latency and cost. • Collaborate with data scientists, software engineers, and product teams to build AI-powered solutions. • Deploy and monitor LLM applications in cloud environments. Requirements • Strong knowledge of Python programming. • Understanding of Large Language Models (LLMs) and Generative AI. • Knowledge of Natural Language Processing (NLP) and prompt engineering. • Experience with LangChain, LlamaIndex, or similar frameworks. • Understanding of RAG architecture, embeddings, and semantic search. • Familiarity with vector databases such as FAISS, Pinecone, or Chroma. • Knowledge of REST APIs and application integration. • Basic understanding of machine learning and deep learning concepts. • Familiarity with Git and cloud platforms such as AWS, Azure, or Google Cloud is an advantage.