Data & AI Engineer

Data & AI Engineer

Summary: Develop and integrate the technical components that capture, store, process, and deliver business context to the client’s existing AI ecosystem.

Responsibilities:

• Develop and maintain the Business Context Repository in a client approved environment, using the architecture and standards established for the project.
• Build data integration pipelines to capture business context from approved sources, including metadata registries, catalogs, workshop outputs, BI reports, and usage information.
• Implement structured storage and retrieval mechanisms for business definitions, ontology relationships, metadata, business rules, and ground truth datasets.
• Integrate the repository with the client’s existing Context Injection component and relevant Graph, semantic, and metadata services.
• Develop Python based automation to extract, transform, validate, and refresh business context.
• Implement LLM assisted and agentic workflows for context drafting, enrichment, review, and maintenance, including human approval controls.
• Build scheduled refresh processes, staleness detection, logging, and monitoring mechanisms.
• Support development of the AI evaluation runner, execute technical integrations, troubleshoot failures, and maintain deployment configurations.
• Deliver reusable source code, configuration, technical documentation, and operational runbooks to the client’s designated repositories.

Required Technical Expertise: Python, SQL, data engineering, API integration, ETL/ELT, LLM integrations, RAG, agentic AI frameworks, structured and unstructured data processing, cloud services, CI/CD, and data governance.