Found Description
What you’ll be doing
We are seeking someone who views the Knowledge Graph not just as a database, but as a living organism that requires constant care, feeding, and pruning. You understand that a RAG system is only as good as the data underlying it. You are intrigued by the complexity of ingesting massive, messy datasets and transforming them into clean, connected knowledge.
- Architecting Graph ETL: Designing and developing robust ETL pipelines specifically for graph ingestion. You aren’t just dumping rows into tables; you are determining how disparate data sources connect, evolve, and relate in a graph structure.
- Data Ingestion at Scale: Managing high-volume data streams using tools like Kafka and implementing CDC (Change Data Capture) patterns to ensure the graph reflects real-time reality.
- Automated Graph Hygiene: Writing scripts and jobs for deduplication, orphan node detection, and data consistency checks. You take pride in a clean schem...