Staff AI Engineer, Data Systems

5+ years building large-scale information systems 2+ years in staff/senior roles Extensive hands-on experience with RAG systems, knowledge graphs, or semantic search platforms Deep experience with graph databases (Neo4j, Neptune, or similar) Understanding of graph structures over relational or vector-only approaches Demonstrated expertise building production RAG systems Familiarity with vector databases (pgvector, Pinecone, Weaviate, Qdrant) Strong understanding of embedding models and fine-tuning approaches Experience with document processing, entity extraction, and text chunking Strong coding skills in Python and/or TypeScript/Node.js Deep understanding of information retrieval theory and semantic search Track record of architecting complex knowledge systems Experience making high-leverage technical decisions about information architecture Mentoring engineers on sophisticated retrieval and graph concepts

Architect and implement graph-based knowledge systems (Neo4j, Neptune) Design and evolve ontologies and schemas for educational content Build GraphRAG systems combining knowledge graph traversal and vector similarity Architect and implement advanced RAG pipelines including hybrid search Design and operationalize embedding pipelines for educational content Design evaluation pipelines to measure retrieval quality Build ingestion systems to process structured and unstructured educational content Implement NLP pipelines for educational content extraction Invent and operationalize long-horizon memory systems for AI agents Design evaluation frameworks for context management Partner with Product, Research, and Educators to understand content requirements Collaborate with ML researchers and engineers on system architecture Guide engineers on knowledge graph design, RAG architecture, and retrieval optimization