Hybrid | Nebraska Avenue Campus, D.C. | 50% Onsite

Active TS/SCI Clearance Required

Summary

Our client is an employee- and service-disabled veteran-owned small business specializing in providing niche technical services. They are a team of experienced cybersecurity professionals with a proven track record of success in federal, Commercial, and academic settings. Additionally, our client designs, builds, operates, and secures scalable cloud and IT infrastructures to meet their customers’ near-term needs and fulfill their long-term requirements.

Responsibilities

Our client is seeking a Graph Database Engineer to join their team! This role is ideal for a data engineering professional with a passion for cutting-edge technologies, such as vector databases and large language models (LLMs). You’ll play a key role in designing and optimizing graph-based solutions, building scalable pipelines, and supporting Retrieval-Augmented Generation (RAG) initiatives in an AWS environment.

• Design, implement, and maintain ETL pipelines tailored to graph-based data structures

• Develop and optimize graph database queries using Cypher, SPARQL, or GQL

• Build and sustain ontologies and knowledge graphs for scalable data modeling

• Integrate vector databases and implement similarity search techniques supporting GraphRAG and RAG workflows

• Collaborate with data scientists and engineers to integrate machine learning models with graph databases

• Apply Large Language Models (LLMs) to meet functional and business use cases

• Ensure data quality, consistency, and security across all engineered solutions

• Communicate with stakeholders to understand business requirements and deliver graph-driven solutions

Requirements

• 6+ years of hands-on experience in data engineering

• 3+ years of experience working with graph databases

• Proficiency in Python and PySpark

• Advanced knowledge of Cypher, SPARQL, or GQL querying languages

• Strong expertise in designing and optimizing ETL processes for graph data

• Experience creating ontologies and presenting data for GraphRAG-based solutions

• Solid understanding of similarity search and RAG implementations using vector databases

• Experience working with Large Language Models (LLMs)

• Excellent written and verbal communication skills

Education/Certification Requirements

• A bachelor's degree from an accredited university is required

Preferred Qualifications

• Engineering experience with AWS systems

• Experience with Neo4j databases preferred

Clearance Requirements

• Applicants selected will be subject to a security investigation and may need to meet eligibility requirements for access to classified information; an active TS/SCI clearance is required.