Senior AI Engineer - LLM, RAG

Architect and build RAG systems combining LLMs (LLAMA, Mistral, Claude, GPT) with structured/unstructured sources; develop AI assistants for industrial diagnostics; build document ingestion/indexing pipelines for semantic search; customize/fine-tune foundational models; and design evaluation strategies for production RAG. Requires an MS/PhD in CS/AI/ML (NLP or deep learning focus), 5+ years ML/AI with NLP/LLM/conversational AI focus, production RAG pipeline experience (LangChain/LlamaIndex/custom vector DBs), prompt engineering/fine-tuning, vector stores (FAISS/Weaviate/Pinecone), and strong Python/PyTorch/Hugging Face.