AI Data Engineer

Location: Warsaw, Poland; hybrid workplace

Company

Dun & Bradstreet helps customers improve business performance through its Data Cloud and Live Business Identity.

What you will do

• Design, build, operate and optimise scalable ingestion pipelines across web data, APIs, SFTP and batch file sources.
• Build and productionise AI pipelines using LLMs and machine learning to extract, classify, enrich, standardise and validate structured and unstructured data.
• Develop agentic and RAG workflows, including prompt design, tool and MCP integrations, orchestration and AI-assisted entity resolution.
• Establish evaluation and monitoring for AI components, including accuracy benchmarks, human review, drift detection, cost and latency tracking.
• Embed data quality, governance and Responsible AI practices while maintaining production health, documentation, lineage and runbooks.
• Partner with product, data science and business stakeholders; contribute to the AI & Ingestion community through reusable patterns, reviews, mentoring and knowledge-sharing.

Requirements

• 5+ years of experience in data engineering or a similar role, including hands-on data ingestion pipeline development.
• Strong Python and SQL skills.
• Practical experience building LLM pipelines or applications using services such as Anthropic, OpenAI or Google Vertex AI/Gemini APIs, including prompt engineering, structured outputs and evaluation.
• Experience with cloud data processing; GCP is preferred, including BigQuery, Dataflow, Cloud Composer/Airflow or Vertex AI. Databricks experience is an advantage.
• Experience with web data collection, APIs, SFTP and other file delivery channels.
• Understanding of AI pipeline engineering practices, including MLOps/LLMOps, version control, CI/CD, automated testing and monitoring.
• Awareness of Responsible AI, data privacy and governance considerations, including GDPR.
• Robust data knowledge, preferably involving business datasets, with analytical and quantitative skills.
• Bachelor’s degree in Data Science, Information Systems, Computer Science, Mathematics or a similar field.
• English fluency and languages relevant to the working market where applicable; ownership, problem-solving, collaboration, continuous learning and knowledge-sharing capabilities.

Nice to have

• Familiarity with RAG, embeddings, vector databases, agent frameworks or MCP.
• Experience or strong interest in communities of practice, internal technical talks or mentoring.

Culture & Benefits

• Hybrid work in Warsaw, Poland.
• Agile collaboration within the AI & Ingestion team and across product, data science and business functions.
• Participation in a community of practice focused on reusable tooling, standards and engineering upskilling.
• Continuous learning through courses, programmes and collaboration with stakeholders, experts, colleagues and mentors.