AI Data Engineer: Ingestion & LLM Pipelines

Dun & Bradstreet Europe; Województwo mazowieckie; On-site; PLN 180,000 - 320,000; Full time

Job summary

Dun & Bradstreet Europe is seeking a Data Engineer II in the AI & Ingestion team to design, build and run production AI pipelines that ingest data from web sources, APIs and file deliveries on our cloud platform. You will apply LLMs to extract, classify, enrich and standardise data while ensuring quality and governance.

You will collaborate with product, data science and business stakeholders, contribute to the AI community of practice, and mentor engineers while monitoring cost and performance

Qualifications

• 5+ years of experience in data engineering or similar, building data ingestion pipelines.
• Strong Python and SQL are minimum requirements.
• Hands-on experience building pipelines or apps with LLMs (Anthropic, OpenAI, Vertex AI) including prompt engineering.
• Experience with cloud data processing (GCP preferred).
• Familiarity with RAG, embeddings and vector databases, MCP is desirable.
• Understanding of MLOps/LLMOps, CI/CD, testing and monitoring.
• awareness of GDPR and Responsible AI principles.

Responsibilities

• Design, build and operate scalable data ingestion pipelines across diverse sources and cloud platform.
• Productionise AI pipelines using LLMs to extract, classify, enrich and standardise data.
• Develop retrieval-augmented generation workflows and MCP integrations.
• Establish evaluation and monitoring for AI components, including accuracy and latency tracking.
• Embed data governance and Responsible AI practices into pipelines and workflows.
• Research data mastering and entity resolution techniques to improve insights.
• Own operational health of ingestion and AI pipelines, including incident response.
• Contribute to and lead AI & Ingestion community of practice and knowledge sharing.
• Support engineers through design/code reviews and mentoring.
• Develop and maintain data flow diagrams, lineage and runbooks.
• Partner with product, data science and stakeholders to translate data requirements into ingestion/AI solutions.

Skills

Python

SQL

LLMs

Data pipelines

Cloud data processing

Education

Bachelor's Degree in Data Science / CS

Tools

BigQuery

Dataflow

Vertex AI

Airflow

Databricks

Job description

Dun & Bradstreet Europe is seeking a Data Engineer II in the AI & Ingestion team to design, build and run production AI pipelines that ingest data from web sources, APIs and file deliveries on our cloud platform. You will apply LLMs to extract, classify, enrich and standardise data while ensuring quality and governance.

You will collaborate with product, data science and business stakeholders, contribute to the AI community of practice, and mentor engineers while monitoring cost and performance