Remote RAG Systems Engineer – Mid

Remote RAG Systems Engineer – Mid-Level · $100 | RemoteAI J RAG Systems Engineer Julian Johansson Full-time · Job · New_York Report this job Apply Now About the role Our product indexes and searches 50 million academic papers for research institutions worldwide. We've built a solid keyword search engine, but our clients want semantic search and AI-generated literature reviews. That's where you come in. You'll design and build the RAG infrastructure that powers our next-generation search: document chunking strategies, embedding pipelines, vector store management, retrieval optimization, and answer generation with proper citations. The scale is significant — we need to handle queries that synthesize information across thousands of papers in seconds. The existing codebase is Python/FastAPI, and we're evaluating LlamaIndex and LangChain for the retrieval layer. You'll make the architecture decisions and implement them. If you've built RAG systems before and know the difference between good retrieval and great retrieval, we need your expertise. Responsibilities - Design and build large-scale RAG infrastructure for academic search - Implement document chunking, embedding, and vector store pipelines - Optimize retrieval accuracy and latency across millions of documents - Build citation tracking and source attribution for generated answers - Own the evaluation framework for retrieval and generation quality Requirements - 3+ years in software engineering with Python - Hands-on experience building RAG systems in production - Familiarity with LlamaIndex, LangChain, and vector databases - Experience with large-scale document processing - SQL proficiency and familiarity with Docker Keep exploring related roles Use these topic pages to discover more roles in the same hiring cluster. Categories NLP & Prompt Engineering MLOps & AI Infrastructure Skills Related remote AI jobs Nearby roles that share similar skills, categories, or hiring inten