Job Requirements
Reston, VA
Top Secret/SCI CI Polygraph
Career Level not specified
Salary not specified
Join Premium to unlock estimated salaries 
Job Description
Program Description:
The program is seeking an experienced engineer to develop the data and retrieval infrastructure supporting a Graph RAG application. This role will focus on transforming structured and unstructured data from multiple sources into reliable, connected knowledge through property graphs, vector search, and database integrations. The engineer will build scalable data pipelines, retrieval services, and MCP tools that enable LangGraph agents to efficiently discover, connect, and retrieve relevant information while maintaining data provenance and source traceability.
Day-to-Day Responsibilities:
Develop Python pipelines to ingest, transform, enrich, chunk, and index structured and unstructured data.
Design property graph models for entities, relationships, provenance, and source traceability.
Develop entity extraction and resolution workflows to correlate information across multiple data sources.
Build embedding pipelines and manage vector indexes for semantic retrieval.
Implement hybrid retrieval using vector, keyword, graph, and database queries.
Develop and integrate MCP servers and tools to expose retrieval capabilities to LangGraph agents.
Integrate Oracle MCP services to enable agent-driven database queries.
Apply graph algorithms to identify relationships, enhance discovery, and optimize retrieval.
Evaluate graph quality, retrieval accuracy, answer grounding, and pipeline reliability.
Partner with application engineers and stakeholders to translate use cases into graph models, retrieval workflows, and agent-based tools.
The program is seeking an experienced engineer to develop the data and retrieval infrastructure supporting a Graph RAG application. This role will focus on transforming structured and unstructured data from multiple sources into reliable, connected knowledge through property graphs, vector search, and database integrations. The engineer will build scalable data pipelines, retrieval services, and MCP tools that enable LangGraph agents to efficiently discover, connect, and retrieve relevant information while maintaining data provenance and source traceability.
Day-to-Day Responsibilities:
Develop Python pipelines to ingest, transform, enrich, chunk, and index structured and unstructured data.
Design property graph models for entities, relationships, provenance, and source traceability.
Develop entity extraction and resolution workflows to correlate information across multiple data sources.
Build embedding pipelines and manage vector indexes for semantic retrieval.
Implement hybrid retrieval using vector, keyword, graph, and database queries.
Develop and integrate MCP servers and tools to expose retrieval capabilities to LangGraph agents.
Integrate Oracle MCP services to enable agent-driven database queries.
Apply graph algorithms to identify relationships, enhance discovery, and optimize retrieval.
Evaluate graph quality, retrieval accuracy, answer grounding, and pipeline reliability.
Partner with application engineers and stakeholders to translate use cases into graph models, retrieval workflows, and agent-based tools.
group id: 10313966
