Job Description
Role Summary
The Data Engineer I develops, via using AI and SQL, and maintains robust data pipelines, manages data migrations and ETL processes, and delivers custom reporting solutions for Greenshades clients. When solutioning, AI is at the forefront of the options considered when building solutions. This role combines deep technical expertise in data integration and file construction with hands-on compliance support for custom report deliverables. The Data Engineer I collaborates cross-functionally, manages work through an Azure DevOps Kanban board, and ensures data flows reliably across systems to meet both client and regulatory requirements.
Responsibilities
- EDI 834 & Ancillary File Development: Build, test, and maintain EDI 834 benefit enrollment files and associated ancillary file formats, ensuring accuracy and compliance with carrier and trading partner specifications.
- Custom Reporting: Create custom reports and dashboards to provide actionable insights to internal and client stakeholders. Includes but not limited to retirement reports, HSA and Benefit file feed creation, as well as WOTC, and related reports.
- Azure DevOps Kanban Management: Manage and track project work items using an Azure DevOps Kanban board, maintaining accurate status updates and prioritization throughout the project lifecycle.
- Collaboration: Work closely with clients and internal teams to understand data requirements and deliver solutions that meet their needs.
- Security and Compliance: Ensure data security and adherence to relevant regulations and industry best practices.
- AI & Agent Development: Design, build, and maintain LLM-powered skills, agents, and automations that accelerate data pipeline, file build, and reporting work, including prompt design, tool integrations, and testing of agent output for accuracy.
- AI Integration & Enablement: Set up and maintain Model Context Protocol (MCP) servers and connectors that give AI agents secure, governed access to internal data sources and tools, and document reusable patterns for the team.
- Other duties as assigned.
Requirements
- 2+ years of experience with ETL and data migration processes in a SQL-focused role
- 2+ years’ experience of proficiency in T-SQL and SQL Server Management Studio (SQL Server 2012+, SSRS, SSIS)
- 1+ years’ experience of hands-on building or working with EDI 834 files and ancillary benefit enrollment formats
- 1+ years’ experience managing work items and project tasks using Azure DevOps Kanban boards
- Strong proficiency in Excel and experience with object-oriented programming
- Experience with common scripting languages
- 1+ years’ experience working with large language models (LLMs) such as Claude, GPT, or similar, including prompt engineering and structured output techniques
- 1+ years’ experience building AI skills and agents, including defining tools/functions, orchestrating multi-step agent workflows, and evaluating agent output for accuracy and reliability
- 1+ years’ experience configuring or developing Model Context Protocol (MCP) servers or similar AI tool-integration frameworks, including authentication, permissions, and connecting agents to databases and APIs
- Understanding of responsible AI practices for sensitive data, including data privacy, access controls, and human review of AI-generated output
- Familiarity with Oracle SQL*Plus is a plus
- Ability to communicate effectively between technical and non-technical stakeholders
- Experience with Jira, GitHub, and Confluence
- BS/BA in Computer Science or related field preferred
- Excellent problem-solving skills, attention to detail, and ability to work independently and as part of a team
This is a remote position.
