Senior AI Engineer – LLM, RAG

BrightAI is hiring a Senior AI Engineer to lead development of Retrieval-Augmented Generation (RAG) systems for industrial troubleshooting. The role involves architecting RAG pipelines, fine-tuning LLMs, and building AI-powered assistants. You'll work with tools like LangChain, LlamaIndex, and vector databases to ingest and index large document corpora.

• Lead architecture and development of RAG systems combining LLMs with external information sources.
• Develop AI-powered assistants for technician diagnosis.
• Build pipelines to ingest, preprocess, and index large document corpora.
• Customize and fine-tune foundational models for domain-specific language.
• Collaborate with product, data, and cloud teams.
• Design evaluation strategies for RAG systems.
• Stay up to date with LLM advances.

• M.S. or Ph.D. in CS, AI, ML or related with NLP or deep learning specialization.
• 5+ years experience in ML/AI with focus on NLP, LLMs, or conversational AI.
• Fluency with LLMs like LLAMA, Mistral, Claude, GPT.
• Experience building RAG pipelines with LangChain, LlamaIndex, or custom vector DB integrations (at least one production system).
• Fluency with prompt engineering, instruction tuning, fine-tuning.
• Deep understanding of document retrieval and vector stores (FAISS, Weaviate, Pinecone).