Data Engineer I

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop, test, and sustain EDI 834 benefit enrollment files along with related ancillary file formats, ensuring precision and compliance with specifications from carriers and trading partners.

• Generate customized reports and dashboards, including retirement reports, HSA and benefit file feeds, WOTC, and other related documentation.

• Oversee and monitor project work items utilizing an Azure DevOps Kanban board, ensuring accurate status updates and prioritization throughout the project lifecycle.

• Collaborate with clients and internal teams to ascertain data needs and deliver appropriate solutions.

• Uphold data security and compliance with relevant regulations and industry best practices.

• Design, develop, and maintain LLM-powered skills, agents, and automations for data pipeline, file construction, and reporting tasks.

• Create prompts, integrate tools, and validate agent outputs for precision.

• Establish and manage Model Context Protocol (MCP) servers and connectors for secure, governed AI-agent access to internal data sources and tools.

• Document reusable AI integration patterns for team reference.

• Build and maintain resilient data pipelines utilizing AI and SQL.

• Oversee data migrations and ETL processes.

• Provide tailored reporting solutions for Greenshades clients.

• Execute additional responsibilities as assigned.

⛳️ Requirements

• Minimum of 2 years of experience in ETL and data migration processes in a SQL-centric role.

• At least 2 years of proficiency in T-SQL and SQL Server Management Studio (SQL Server 2012+, SSRS, SSIS).

• Over 1 year of hands-on experience building or working with EDI 834 files and ancillary benefit enrollment formats.

• More than 1 year of experience managing work items and project tasks through Azure DevOps Kanban boards.

• Strong Excel proficiency and experience with object-oriented programming.

• Familiarity with common scripting languages.

• Over 1 year of experience working with large language models (LLMs) such as Claude, GPT, or similar, including prompt engineering and structured output techniques.

• More than 1 year of experience in developing AI skills and agents, including defining tools/functions, orchestrating multi-step agent workflows, and assessing agent output for accuracy and reliability.

• Over 1 year of experience configuring or developing Model Context Protocol (MCP) servers or similar AI tool-integration frameworks, including authentication, permissions, and linking agents to databases and APIs.

• Knowledge of responsible AI practices for sensitive data, including data privacy, access controls, and human review of AI-generated outputs.

• Familiarity with Oracle SQL*Plus is an advantage.

• Capable of effective communication between technical and non-technical stakeholders.

• Experience with Jira, GitHub, and Confluence.

• Exceptional problem-solving abilities, attention to detail, and the capacity to work independently as well as part of a team.

• Applicants must be residing in the United States.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance.

• Flexible work hours and remote work options.

• Opportunities for professional development and career advancement.

• Supportive and inclusive company culture.