AI Data Engineer

Skill Requirement : • Healthcare or payer domain experience, especially with member, claims, provider, quality, or reference data. • Snowflake SQL: Highly skilled. Must be able to develop complex transformations, optimize performance, and work confidently with CTEs, advanced joins, and analytic/window functions. • Snowflake Data Engineering: Strong real-world experience building curated data layers using medallion architecture principles across bronze, silver, and gold datasets. • Semantic Modeling / Semantic Layer Engineering: Must be able to define business-friendly metrics, dimensions, grain, relationships, and reusable semantic views on top of Snowflake data. • Snowflake Cortex / AI-Enabled Analytics: Experience supporting Snowflake Cortex-based analytics workflows, semantic intelligence, or agentic analytics use cases is strongly preferred. • Data Quality, Profiling, and Validation: Must be able to identify natural and surrogate keys, assess cardinality and distribution, validate transformations, and ensure trustworthy semantic outputs. • Strong communication and ownership: Able to work across engineering, product, and analytics partners, clarify requirements, and proactively drive work with limited direction. “Desirements” • Experience in evaluating / troubleshooting and measuring agent performance, identifying issues, and optimizing it • Experience with dbt, semantic view design, or governed self-service analytics patterns. • Python experience for automation, metadata processing, data validation, or AI-assisted engineering workflows. • Exposure to agentic AI, natural language analytics, or Snowflake Cortex Analyst / Cortex Search use cases. Specific technologies to be used and level of proficiency : • Snowflake SQL: Highly skilled to expert level. • Snowflake: Strong hands-on experience with performance tuning, secure data design, and curated data modeling. • Semantic Modeling / Semantic Views: Strong proficiency in defining business metrics, dimensions, relationships, grain, and reusable semantic abstractions. • dbt: Preferred real-world experience developing modular transformations, tests, and deployment patterns. • Snowflake Cortex: Preferred experience with Cortex-enabled analytics, semantic intelligence, or agent-supporting workflows. • Python: Some experience desired, with preference for intermediate or higher skill for automation and validation use cases. Day to day Job Description of a Senior Data AI Engineer role: • Design and implement scalable Snowflake data models and pipelines that align with business objectives and agentic AI use cases. • Build curated bronze, silver, and gold data layers and reusable semantic assets that support trusted analytics and natural-language data access. • Collaborate with product, analytics, and engineering partners to translate complex requirements into governed data products and semantic models. • Optimize Snowflake queries, warehouse configurations, and transformation performance for reliability, scalability, and cost efficiency. • Design and implement data quality validation, profiling, and testing strategies to improve trust in downstream semantic outputs. • Contribute to lineage-aware transformation patterns, documentation, and engineering standards for reusable data assets. • Use dbt where applicable to develop modular transformations, tests, and deployment patterns; prior hands-on dbt experience is preferred. • Support Snowflake Cortex-enabled analytics, semantic intelligence, and agent-assisting workflows where applicable. • Troubleshoot production issues and implement durable long-term solutions. • Document architectural decisions, semantic definitions, and data lineage.