GraphRAG Engineer

This is a fully remote position, open to applicants in Spain, +2 more countries.

📋 Description

• Provision, optimize, and sustain production-quality Neo4j graph databases and pgvector vector storage clusters.

• Design high-throughput indexing structures, cosine similarity vector indexes, and query enhancements for sub-second response times.

• Create automated data ingestion pipelines that parse Git repositories, abstract syntax trees (ASTs), Jira issue links, Apache Avro schemas, and CI/CD metadata into an enterprise knowledge graph.

• Link distributed pipeline engines to hybrid retrievers that integrate SQL, Cypher graph traversals, and dense vector embeddings.

• Set up circuit breakers, confidence scoring thresholds, and step-limit constraints for autonomous agents.

• Integrate microservices and knowledge repositories with the Enterprise AI Gateway.

• Maintain version-controlled system prompt structures in localized .ai/ spoke directories while adhering to DLP PII scrubbing guidelines and token rate limits.

• Implement automated failover, backup restoration, and multi-cloud storage-tier cost management across AWS and GCP.

• Take ownership of the semantic, vector, and graph storage layer that drives the context engine for enterprise AI utilities and the Internal Developer Portal.

• Lead the deployment of the SDLC Context Graph and GraphRAG Engine for CAB compliance, code/schema lineage tracking, and enterprise LLM proxy integrations.

⛳️ Requirements

• Extensive operational and development experience with Neo4j (Cypher, APOC, causal clustering) or enterprise Knowledge Graphs.

• Demonstrated expertise with pgvector (PostgreSQL), embeddings management, hybrid search methodologies, and framework integrations (LangChain, LlamaIndex, or custom RAG pipelines).

• Practical experience managing relational (PostgreSQL) and graph databases within AWS and GCP cloud environments.

• Proficient in consuming Apache Avro payloads, streaming Kafka events (AWS MSK), and parsing both structured and unstructured code and JSON artifacts.

• Solid understanding of Prompts-as-Code patterns, few-shot prompt optimization, and tool specification for agents.

• Experience with Infrastructure-as-Code (Terraform) principles, Kubernetes (EKS/GKE), Docker, and pull-based GitOps workflows.

• Familiarity with HashiCorp Vault Transit encryption, OIDC keyless authentication, and zero-trust workload identities.

• Knowledge of OpenTelemetry (OTel) instrumentation for monitoring vector search query latencies and LLM inference performance in Datadog or Grafana.

🏝️ Benefits

• Generous PTO Policy.

• Unplugged Days supporting work-life balance.

• Flexible Work From Home Policy.

• Mental & Physical Wellness programs.

• Phone and Internet Reimbursement program.

• Access to Continued Career Development.

• Comprehensive Benefits and Competitive Packages.

• Paid Volunteer Time.

• Employee Resource Groups.