Overview You will build and maintain the Graph RAG platform that powers enterprise AI utilities and the Internal Developer Portal. The role sits at the intersection of graph databases, vector storage, and AI-driven pipelines, connecting AWS MSK with knowledge graphs across AWS and GCP. You will enable automated governance, code lineage, and LLM integrations while optimizing for scalable, low-latency retrieval. This is a hands-on, multi-cloud, data-centric role with a clear impact on enterprise AI tooling and governance. Compensaciones / Incentivos Generous PTO Unplugged Days Flexible WFH Wellness programs Phone and Internet Reimbursement Continued Career Development Responsabilidades Provision, tune, and operate production graph database clusters (Neo4j) and vector stores (pgvector) with performance optimizations Build automated ingestion pipelines to convert Git repos, ASTs, Jira links, Avro schemas,



and CI/CD metadata into a knowledge graph Orchestrate distributed pipeline engines to support hybrid retrievers for AI-powered developer workflows Configure safeguards, thresholds, and constraints to prevent runaway autonomous agent execution Integrate microservices and knowledge stores with the Enterprise AI Gateway and manage prompt structures under DLP/PII rules Implement automated failover, backups, and multi-cloud storage cost controls across AWS and GCP Requisitos principales Deep experience with Neo4j (Cypher, APOC, causal clustering) or enterprise knowledge graphs Expertise with pgvector, embeddings management, and hybrid RAG pipelines Hands-on DB administration for Postgre SQL and graph databases in AWS and GCP Data/pipeline experience with Apache Avro, Kafka (AWS MSK), and parsing code/JSON artifacts Practical understanding of Prompts-as-Code, few-shot prompt optimization, and agent tooling Neo4j (Cypher, APOC, causal clustering) pgvector Postgre SQL Apache Avro Kafka (AWS MSK) Lang Chain or Llama Index (or similar)

📌 Graphrag engineer - cloudera (Barcelona)
🏢 Jobrapido
📍 Barcelona