GraphRAG AI Engineer - Build a Neo4j + LangGraph Knowledge Graph RAG System for Research Papers

We're looking for an experienced AI Engineer to build a GraphRAG (Graph Retrieval-Augmented Generation) system that helps researchers connect findings across thousands of academic papers. The system will ingest papers from ArXiv, extract entities (authors, venues, concepts), construct a citation/knowledge graph in Neo4j, and enable question-answering with cited, graph-grounded answers. Responsibilities: Build a paper ingestion pipeline (ArXiv API/scraping, PDF parsing) Implement entity extraction (authors, venues, concepts, citations) using LLMs Design and populate a Neo4j graph schema (Paper, Author, Venue, Concept nodes) Build the GraphRAG retrieval layer combining vector similarity search + graph traversal Integrate OpenAI embeddings for semantic search Orchestrate the pipeline with LangGraph Expose functionality via a FastAPI backend Add Neo4j graph visualization for citation networks Implement multi-document reasoning for cross-paper research gap identification Ensure answers include proper citations back to source papers Required Skills: Strong Python experience Hands-on experience with Neo4j (Cypher queries, graph modeling) Experience with LangChain/LangGraph Experience with OpenAI API / embeddings Understanding of RAG and GraphRAG architectures FastAPI (or similar) backend development Familiarity with NLP entity/relation extraction Bonus: experience with ArXiv data, academic citation graphs, or Streamlit for quick prototyping UIs