Role: Data Engineer (Amazon Neptune, SPARQL, GraphRAG, Python, Data Engineering)
Location: Chicago, IL 60606 (Hybrid Setup)
Duration: 6 Months (Target Start: 10/01/2026 - End: 03/31/2027)
Pay Rate: $62.00/hr on W2.
Note : Only W2 candidate apply only.
Professional Job Description
Position Overview
Seeking a Data Engineer / Lead Consultant with 10+ years of overall IT experience to design, build, and maintain production-scale enterprise graph database platforms.
The position requires deep expertise in Amazon Neptune, SPARQL / Gremlin, GraphRAG, and Python-based data engineering pipelines.
The ideal candidate will integrate knowledge graphs into GenAI / GraphRAG frameworks to improve contextual grounding and partner with AI teams to implement hybrid search architectures combining graph traversals with vector databases.
Key Responsibilities
* Graph Architecture & Platform Building: Design, deploy, and optimize production-scale instances of Amazon Neptune using SPARQL and/or Gremlin query languages.
* GraphRAG & GenAI Integration: Integrate enterprise knowledge graphs into GraphRAG pipelines to minimize AI hallucinations and enhance contextual grounding; collaborate with AI engineering teams on hybrid search models merging graph traversals with vector DBs.
* Data Engineering & ETL Pipelines: Build, maintain, and monitor scalable ETL/ELT pipelines using Python or JVM environments (Java/Scala) integrated with core AWS infrastructure (S3, RDS, ECS).
* Technical Leadership & Stakeholder Management: Serve as a Lead Consultant driving data platform strategy, code reviews, and direct communication with project stakeholders.
Required Qualifications
* Experience: 10+ years of total IT experience in Big Data, NoSQL, and Graph Database engineering.
* Core Technical Stack: Advanced hands-on experience with Amazon Neptune, SPARQL, Gremlin, GraphRAG, and Python (or Java/Scala).
* AWS Cloud Infrastructure: Strong proficiency with AWS core services, specifically AWS S3, Amazon RDS, and Amazon ECS.