Position Details
About this role
Specialist, Data Engineer builds and maintains AI-enabled data pipelines and ML services, focusing on production-grade LLMs, RAG workflows, and API-driven automation in a hybrid setup.
Key Responsibilities
- Design and refine prompts and agent workflows for LLMs
- Develop data pipelines and AWS Redshift integration
- Build and deploy inference stacks and managed services
- Implement API-driven automation and integrations
- Establish model evaluation practices
Technical Overview
Role centers on prompts, LLM integration, data pipelines with AWS Redshift, and evaluation frameworks; emphasizes production readiness and integration with BI tools like Power BI.
Ideal Candidate
The ideal candidate is a data engineer with 3+ years applying prompt engineering and LLMs in production, strong Python and data pipeline experience, and familiarity with AWS Redshift and Power BI/Power Automate for analytics and automation.
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Clearance & Visa
Keywords for Your Resume
Deal Breakers
No visa sponsorship, Inability to work in a hybrid model in Rahway, NJ, Lack of Python/data engineering experience, No experience with LLMs or prompt engineering
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile