GraphRAG Engineer

Location and Travel Details: Remote

Join our Data Science Team! Our collaborative and diverse data science team is focused on helping organizations unlock business value through machine learning, analytics, generative AI, agentic AI systems, and intelligent automation. We work across industries including sustainment, logistics, industrial modernization, acquisition, cybersecurity, retail, and manufacturing to design and implement solutions that solve complex business challenges. Our projects range from creating analytic insights from data to enterprise-level end-to-end knowledge engines supporting application development. We apply natural language processing (NLP), computer vision, sensor analytics, knowledge graphs, large language models (LLMs), retrieval augmented generation (RAG), agentic workflows, statistical modeling, visualization, and human-in-the-loop decision systems to provide world class solutions.

We are seeking a skilled Graph RAG Engineer to design, build, and operationalize a Graph-based Retrieval-Augmented Generation (GraphRAG) system. This role sits at the intersection of knowledge graph engineering, data pipeline development, and applied AI. The ideal candidate will develop Python-based automation to discover and extract relevant features from structured and unstructured data sources, populate a graph database, and build agentic AI workflows on top of that knowledge graph. They will shape how structured knowledge is extracted, organized, and reasoned over at scale, with direct impact on mission-critical analytical products.

Key activities include: 

• Architect, design, build, and extend GraphRAG solutions that combine knowledge graphs, graph databases, retrieval pipelines, and large language models
• Design graph schemas, ontologies, taxonomies, metadata models, and graph data models tailored to domain-specific business and analytical use cases
• Develop Python scripts and modules to automate entity extraction, entity resolution, relationship extraction, feature discovery, metadata capture, tagging, and graph enrichment
• Build and populate graph databases using extracted concepts, relationships, source evidence, and domain-specific ontologies
• Create repeatable data ingestion and transformation pipelines for structured, semi-structured, and unstructured data sources
• Integrate graph databases and graph query results into retrieval-augmented generation workflows and LLM context windows to improve answer accuracy, explainability, and traceability
• Develop and apply AI agents or agentic frameworks that interact with GraphRAG systems and support multi-step reasoning and query resolution
• Implement validation, traceability, lineage, and quality checks for generated graph data, retrieval outputs, and graph structure
• Collaborate with domain experts, data engineers, AI engineers, ML engineers, and solution architects to translate business needs into GraphRAG capabilities and document designs, data flows, graph structures, automation logic, and integration points

Do you have what it takes? Are you driven to solve complex business problems with cutting-edge AI technologies? Do you enjoy experimenting with emerging frameworks, evaluating new models, and designing intelligent systems that create measurable impact? We value curiosity, innovation, collaboration, and the ability to communicate technical concepts to diverse audiences.

Required skills for this job include:

Graph Database Development

• Demonstrated experience building and populating a property graph database
• Proficiency in Cypher query language for graph traversal, filtering, and aggregation
• Ability to design node/relationship schemas and ontologies from scratch

GraphRAG Implementation

• Hands-on experience building a GraphRAG system — including graph-aware retrieval, entity linking, and context injection into LLM prompts
• Understanding of how graph structure improves over flat vector search for multi-hop or relational queries

Python Development

• Strong Python skills, including object-oriented design, modular package development, and scripting for data automation.
• Experience with NLP or information extraction libraries such as spaCy, transformers, LangChain, LlamaIndex, or similar for automated feature and entity discovery

Agentic AI Frameworks

• Experience developing or extending LLM-based agents using frameworks such as LangGraph, LangChain Agents, AutoGen, CrewAI, or similar
• Ability to chain tools, memory, and graph lookups within an agentic loop

General

• Strong debugging, documentation, and software engineering practices
• Ability to work with technical and non-technical stakeholders to understand data meaning and business context

Desired skills for this job include:

• Experience with graph ML libraries such as PyG (PyTorch Geometric) or NetworkX for graph analytics or embedding generation.
• Familiarity with knowledge graph embedding models (TransE, Node2Vec, GraphSAGE) to enhance retrieval.
• Experience with vector databases (Pinecone, Weaviate, Chroma) used in hybrid graph + vector retrieval architectures.
• Prior work in a government, defense, or intelligence community environment.
• Experience with ETL/ELT pipelines and orchestration tools such as Airflow, Prefect, or dbt.
• Familiarity with Azure OpenAI, AWS Bedrock, or on-premise LLM deployments for air-gapped or controlled environments.
• Understanding of data provenance, traceability, and explainability requirements in regulated or classified settings.
• Experience with Microsoft GraphRAG (open-source) or similar production GraphRAG implementations.
• Must have or be willing to obtain Secret Clearance (this requires US Citizenship)
• Ability to pass required background screening and drug testing

Education:

• Bachelor's degree in Computer Science, Data Science, Engineering, or a related field — or equivalent demonstrated experience
• Advanced degree a plus but not required

About ILW 

At Illumination Works, we know data, and we should, we’ve been doing it since we started in 2006! We specialize in everything data from big data to data science, data engineering, software engineering, and cloud design. We are a trusted technology partner in user-centered digital transformation—delivering impactful business results to clients. We partner with customers to solve their unique technology and data challenges and stay on top of modern technologies and advancements leveraging our Innovation Lab. Check out our website to learn more at www.ilwllc.com. 

Why choose us? We invest in our employees in all aspects of their life and we value family. We offer market-competitive salary, a generous PTO package, and comprehensive medical, dental, vision and life insurance plans. We also offer 401K, short/long-term disability insurance, a fun and engaging culture, and training opportunities to keep you up to speed on the latest technologies. 

Commitment to Non-Discrimination

All qualified applicants will receive consideration for employment without regard to disability, status as a protected veteran, or any other status protected by applicable federal, state, local, or international law.

Know Your Rights Poster

E-Verify Participation Poster (uscis.gov)

Accommodations
If you are an individual with a disability and would like to request a reasonable workplace accommodation for any part of our employment process, please contact the Human Resources Staff by sending an email to [email protected]. This option is reserved only for individuals who are requesting a reasonable workplace accommodation. It is not intended for other purposes or inquiries. 

Notification for current or previously cleared professionals:

Official U.S. Government information appearing in the public domain shall not automatically be considered UNCLASSIFIED or approved for public release. ILW recognizes that information contained in resumes of current or previously cleared professionals may be sensitive, containing potentially proprietary and/or protected information. Protected Information is considered classified, in the process of a classification determination, or unclassified, but protected by statute. Therefore, all resumes should be approved for public release by a U.S. Government Official with Original Classification Authority, prior to posting the resume to ILW’s applicant tracking system.

 
By submitting my resume, I understand that I am NOT authorized to upload content with Official U.S. Government information that is considered, sensitive, proprietary, or protected.