Cadre AI

Data Engineer

• Design and build medallion lakehouses on Databricks, Microsoft Fabric, and Snowflake
• Own ingestion from ERPs, CRMs, and SaaS platforms, including change data capture and schema drift handling
• Model and transform data with dbt and orchestrate pipelines with Airflow, Dagster, or Lakeflow Jobs
• Ship pipelines through CI/CD using GitHub Actions and Declarative Automation Bundles
• Build data quality checks and data contracts into pipelines
• Configure and govern coding agents in client Databricks repositories
• Build production RAG pipelines including parsing, OCR, chunking, embeddings, hybrid retrieval, and reranking
• Design GraphRAG systems using knowledge graphs and graph stores
• Select and justify retrieval architectures based on use case, cost, and maintenance
• Operate vector, full-text, and hybrid search infrastructure with incremental indexing and permission-aware retrieval
• Build and deploy retrieval-backed agents on Databricks Agent Bricks
• Create governed semantic and metric definitions across dbt, Power BI, Cube, Databricks, and Snowflake
• Lead data readiness assessments and document business logic, gaps, and remediation
• Expose governed data to agents through MCP
• Build golden datasets, evaluation pairs, and leakage-free backtesting splits
• Instrument retrieval and agent pipelines and track recall, precision, groundedness, experiments, and model versions
• Monitor drift, freshness, and production data gaps
• Implement RBAC, row-level security, and masking across data and retrieval systems
• Ensure data paths meet SOC 2 and client AI governance requirements
• Work with client IT, finance, and operations leaders on scope, access, and build-versus-buy decisions
• Record architecture decisions and contribute reusable engineering blocks to Cadre’s internal library

Explore Senior AI Data Engineer at Cadre AI. Review requirements and application details.

Open roles

Senior AI Data Engineer