AI Data Engineer
About The Position
There is a strategic opportunity within EDAO to build and implement AI-assisted engineering capabilities across 31 production dbt projects in the Marketing Analytics portfolio. The initiative will integrate GitHub Copilot with dbt, Snowflake, GitLab, Jira, Confluence, dbt Cloud, and CTM workflows to accelerate delivery while maintaining governance and human oversight. The selected candidate will contribute to AI-driven engineering solutions spanning requirements analysis, impact assessment, development, automated testing, deployment orchestration, reconciliation, and production support. The role supports pilot implementation, developer enablement, troubleshooting, and scaled adoption across the dbt project estate, working with developers, technical leads, architects, QA teams, platform teams, and deployment stakeholders throughout the lifecycle.
Requirements
- Skill set: dbt, Snowflake, Python, and AI.
Responsibilities
- Design and build reusable AI skills, prompts, agents, and instruction files for dbt and data engineering workflows.
- Develop AI capabilities for Jira story intake, impact analysis, technical design, dbt model generation, testing, and code review.
- Build automation for CTM configuration validation, dependency sequencing, scheduling alignment, and deployment-readiness checks.
- Develop deployment skills covering GitLab merge requests, CI/CD pipelines, dbt Cloud execution, release runbooks, and change evidence.
- Build automated regression-testing and data-reconciliation capabilities across development, pre-production, and production environments.
- Apply hands-on knowledge of dbt models, macros, materializations, incremental strategies, tests, documentation, lineage, and dbt Fusion.
- Use Snowflake metadata, dbt manifests, GitLab repositories, and lineage information to identify upstream and downstream change impacts.
- Develop Python-based automation for API integration, metadata processing, validation, structured outputs, and workflow orchestration.
- Create reusable engineering standards for SQL, dbt, testing, data modeling, error handling, observability, and repository structure.
- Build AI-assisted support for pipeline monitoring, data freshness, anomaly analysis, defect investigation, and production reconciliation.
- Integrate AI-assisted workflows with GitHub Copilot, Jira, Confluence, GitLab, Snowflake, dbt Cloud, CTM, and approved MCP servers.
- Create golden datasets and evaluation scenarios to measure AI-draft acceptance, accuracy, rework, test coverage, and edge-case handling.
- Review AI-generated artifacts for business-logic accuracy, maintainability, security, performance, and compliance with project standards.
- Support pilot implementation, developer enablement, troubleshooting, and scaled adoption across the dbt project estate.
- Collaborate with developers, technical leads, architects, QA teams, platform teams, and deployment stakeholders throughout the lifecycle.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Education Level
No Education Listed
