Job Description & Details
This contract gig places you right at the intersection of data engineering and AI automation, helping modernize 31 production dbt projects within a major Marketing Analytics portfolio. If you enjoy building internal tooling and integrating LLMs into actual data pipelines rather than just talking about AI, this is a solid project to sink your teeth into.
What You'll Actually Be Doing
Your day-to-day will involve designing and implementing AI-assisted workflows using GitHub Copilot alongside standard data tooling like dbt and Snowflake. You'll build custom prompts, reusable skills, and automation scripts to handle everything from Jira story intake and impact analysis to dbt model generation and GitLab CI/CD deployments. You aren't just writing standard SQL models here; you're engineering the systems that help other developers write, test, and deploy code faster while keeping strict data governance in place.
The Core Tech Stack
You need deep, hands-on muscle memory with dbt (models, macros, materializations, incremental strategies) and Snowflake, paired with strong Python scripting skills for API integrations and metadata processing. Familiarity with GitHub Copilot extension points, GitLab CI/CD pipelines, and data observability is non-negotiable since you'll be bridging the gap between raw LLM outputs and enterprise-grade data pipelines.
Interview Expectations
Expect the hiring team to ask you how you handle hallucination and context limitations when integrating LLMs into programmatic dbt workflows. They want to hear about your strategies for deterministic validation, such as using automated test coverage and metadata checks to verify that AI-generated SQL actually executes correctly without breaking upstream or downstream lineage. They'll also likely test your Python capabilities regarding metadata parsing and API orchestration with tools like Snowflake and Jira.
Application Advice
To make it past the ATS, your resume needs to explicitly highlight your experience with dbt, Snowflake, Python, and AI tool integrations. Don't just list technologies; write out specific bullet points showing how you have automated data pipelines, built custom Python scripts for metadata processing, or integrated LLMs/Copilot into software or data engineering workflows.