Knowledge Graph Data Engineer
Bespoke Technologies · Reston, VA
BT-473 – Knowledge Graph Data Engineer
Location: Reston, VA
**Please do NOT apply if you do not have an active Poly clearance. Those without a Poly will not be considered.**
We are seeking a highly experienced and motivated Knowledge Graph Data Engineer to build the data and retrieval foundation for a Graph RAG application. The system combines a property graph, vector search, and database queries with a LangGraph agent. You will help turn information from multiple sources into reliable graph data and make it accessible through retrieval APIs and MCP tools.
Role Description:
- Build Python pipelines to ingest, clean, chunk, enrich, and index structured and unstructured data.
- Model entities and relationships in a property graph, preserving provenance and links to source material.
- Develop entity extraction and resolution workflows that connect information across sources.
- Build embedding pipelines and maintain vector indexes for semantic search.
- Implement hybrid retrieval that combines vector search, keyword search, graph traversal, and database queries.
- Develop and integrate MCP servers and tools that expose vector search capabilities to a LangGraph agent.
- Integrate the Oracle MCP server so the agent can query relevant database data.
- Apply graph algorithms to identify connections and improve retrieval.
- Evaluate graph quality, retrieval relevance, answer grounding, and pipeline reliability.
- Collaborate with application engineers and stakeholders to turn use cases into graph models, retrieval workflows, and agent tools.
- Required qualifications
- Strong computer science fundamentals, including data structures, algorithms, software design, and testing.
- Proficiency in Python and experience building maintainable data pipelines or backend services.
- Working knowledge of cloud fundamentals, including compute, storage, networking, security, and deployment.
- Hands-on experience with property graph modeling, queries and traversals, and graph algorithms.
- Experience with embeddings, vector indexes, and semantic or hybrid search.
- Understanding of retrieval-augmented generation and how to evaluate the quality of retrieved context.
- Ability to work with inconsistent or incomplete data and communicate technical decisions clearly.
Preferred qualifications:
- Experience with Oracle Cloud Infrastructure (OCI), Oracle Database, or Oracle Property Graph.
- Experience building agents with LangGraph or a similar framework.
- Experience developing or integrating Model Context Protocol (MCP) servers and tools.
- Familiarity with entity resolution, information extraction, or knowledge graph construction.
- Experience with CI/CD, containers, infrastructure as code, and production monitoring.
Required Credentials:
- 10+ years of experience relevant to this position.
- Bachelor’s Degree in engineering, Math or computer science. Master’s degree preferred.