About the job
The AI Data Engineer builds and maintains the data infrastructure that powers AI applications across Legal Operations. You will design and implement data pipelines that ingest from legal systems, transform data into AI-ready formats, load vector databases and other AI stores, and expose data services through APIs. This role is embedded within the AI team and works in close partnership with AI and data colleagues to ensure AI systems have reliable, high-quality data at every stage.
Responsibilities
• Design and implement data pipelines that ingest, transform, and deliver data from legal systems (matter management, eBilling, CLM, document management) to AI applications
• Build and maintain pipelines that load and refresh vector databases, document stores, and graph databases used by AI retrieval systems
• Engineer data transformations that prepare legal data for AI consumption — chunking, embedding generation, metadata enrichment, and schema normalization
• Build upstream and downstream integrations with MCP (Model Context Protocol), vector databases, and knowledge graphs to support context engineering and AI retrieval systems
• Develop and maintain APIs that expose structured and unstructured data to AI applications and analytics tools
• Implement data quality checks and validation at pipeline ingestion points to ensure AI systems receive reliable, complete data
• Build monitoring and alerting for pipeline health, data freshness, and load failures
• Understand AI data access patterns and optimize data delivery for AI performance
• Integrate with the semantic layer — consuming entity resolution outputs, taxonomy mappings, and enriched datasets to ground AI applications
• Implement ETL/ELT processes using dbt, Fivetran, or similar tools with a focus on reliability and maintainability
• Document pipeline designs, data contracts, and operational runbooks
Qualifications
Minimum
Bachelor's degree in Computer Science, Data Science, Information Systems, or related field (or equivalent experience); Master's degree preferred
4+ years of experience in data engineering related to AI application
Strong proficiency in SQL and Python for data engineering and transformation
Experience with cloud data platforms (Snowflake, Databricks, BigQuery, or similar)
Experience with ETL/ELT tools (dbt, Fivetran, Airflow, or similar)
Experience building and maintaining REST APIs
Understanding of data modeling and data transformation best practices
Experience with version control (Git) and CI/CD practices
Ability to work closely with AI/ML teams and understand their data requirements
Preferred
Experience with vector databases (Pinecone, Weaviate, Chroma), embedding generation pipelines, document stores (MongoDB or similar) and their integration patterns
Understanding of RAG, MCP architectures, context engineering principles, and how data quality affects retrieval performance
Experience with semantic layer technologies (dbt Semantic Layer, Cube, AtScale), knowledge graphs (Neo4j), or ontology design
Experience with streaming or event-driven data architectures (Kafka or similar)
Familiarity with legal operations data (matter management, eBilling, CLM, document management)