Data and Analytics Engineer

Role overview This position blends insurance industry knowledge with full-stack data and analytics engineering to construct the data foundations that an enterprise AI platform depends on. The focus is on the layers that make AI dependable: clean, well-modeled data, governed pipelines, and semantic models that translate business meaning into natural-language interfaces. The work spans designing rigorous data models, building pipelines, and creating the semantic layer that sits between raw data and AI agents.

Responsibilities - Architect flexible, performant data models that move line-of-business teams toward a single source of truth within their domains. - Use SQL, Python, dbt, and a cloud data warehouse to build and maintain infrastructure for reporting, analysis, and automation. - Perform data QA, develop automated testing for data models, and contribute to data governance (permissions, lineage, definitions, access controls). - Build semantic data models that allow business stakeholders to ask questions in plain language, defining the metrics, dimensions, and relationships AI agents need. - Identify and resolve gaps in data structure, naming, and coverage that could cause AI agents to produce incorrect results. - Author semantic view configurations and skill files in YAML and Markdown, document playbooks and reusable templates, and run technical workshops to upskill teammates.

Requirements - 8+ years in analytics engineering, data engineering, or a related technical role, with at least some customer-facing or cross-functional experience. - Advanced SQL fluency (CTEs, window functions, incremental pipeline patterns) and strong experience with dbt projects, including testing, documentation, and CI/CD pipelines. - Modern, type-hinted Python, comfort with Git workflows, and a track record of shipping production data models that non-technical users rely on. - Daily use of an AI coding assistant (such as an LLM-based IDE) as a primary development environment. - Hands-on semantic modeling experience, including writing structured skill files that encode enough domain knowledge for an agent to behave like a subject-matter expert. - Strong client-facing communication skills, with the ability to translate technical capabilities into what a business leader actually needs, plus experience with Cortex-style tools (analyst, agents, search, dynamic tables).

Nice to have - Experience with Airflow or similar orchestration frameworks. - Familiarity with enterprise business systems such as ERP, CRM, or HRIS.