AI Data Engineer (R-20104)
Core
Design, build, and operate scalable data ingestion pipelines using AI and LLMs to collect, extract, enrich, and validate data for Dun & Bradstreet's Data Cloud.
Role type
Senior IC AI Data Engineer
Builds
Production AI pipelines for data ingestion, extraction, classification, and entity matching
Domain
Data Engineering, Generative AI, Cloud Infrastructure
Deliverable
production ML models
Required skills
Cloud-native data engineering, Large Language Models (LLMs), Agentic workflows, Retrieval-Augmented Generation (RAG), Prompt engineering, Model Context Protocol (MCP), Data quality governance, Entity resolution, Drift detection, Human-in-the-loop systems
Preferred skills
Data mastering techniques, Responsible AI practices
Technologies
Cloud data platforms, LLMs, MCP, RAG frameworks
Responsibilities
Design and operate scalable data ingestion pipelines across web, API, and batch sources; Build and productionize AI pipelines using LLMs for data extraction and standardization; Develop agentic and RAG workflows with prompt design and orchestration; Establish evaluation and monitoring for AI components including accuracy benchmarks and drift detection; Embed data quality, governance, and Responsible AI practices into pipelines; Research and apply data mastering and entity resolution techniques.
Seniority
Senior, hands-on IC