Remote roles building retrieval-augmented generation systems — vector search, embeddings, chunking, and grounding LLMs in real data. On Inferr, every candidate is verified by proof of work, so teams hire on shipped retrieval systems, not résumés.
There are no open rag engineer roles on the board at this moment. Build your verified profile now so you're the first match when one opens — or browse every remote AI role.
A RAG engineer builds retrieval-augmented generation pipelines — indexing data into a vector store, retrieving relevant context, and grounding LLM responses to reduce hallucination and improve accuracy.
Common requirements include vector databases (pgvector, Pinecone, Weaviate), embedding models, chunking and reranking strategies, and frameworks like LangChain or LlamaIndex, plus production LLM experience.