Director, Analytics Engineering

Responsibilities

• Build and own a trusted semantic model, with governed metrics and business definitions, that answers business questions consistently across every tool
• Build evals and ground-truth datasets that measure answer quality, and use them to drive improvements and catch regressions
• Instrument telemetry to see who uses the semantic model and AI tools, what they ask, and where they get stuck
• Build a model-selection harness so GitLab can route work across LLMs and stay flexible on cost and quality
• Own data modeling and curated datasets for self-service, with the ownership, data contracts, testing, and documentation that make them AI-ready
• Define the AI data access strategy: when to use BI, Claude, MCP servers, or Slack agents, with the governance and security to keep access trusted and reliable
• Own the enterprise BI and self-service tools strategy (e.g., Tableau, Omni), including evaluation, adoption, and cost
• Build self-service capabilities, such as Claude skills, documentation, and guided workflows, that help people find and use data on their own
• Build and own company-wide data applications, from Claude-built single-page apps to apps inside BI tools, that combine Snowflake data, API calls, AI-powered deep dives, and write-back to Postgres or Snowflake
• Set engineering standards for data apps (security, authentication, testing, deployment, and monitoring) so they're reliable at company scale

Languages