AI Data Engineer (R-20104)
Dun & Bradstreet13 days ago
Warsaw, PolandMid Level
Responsibilities
- Design, build, and operate scalable data ingestion pipelines for web data, APIs, and batch file deliveries.
- Build and productionize LLM and machine learning pipelines for data extraction, classification, enrichment, standardization, and entity matching.
- Develop agentic and RAG workflows with prompt design, tool integrations, MCP integrations, and orchestration.
- Establish AI evaluation and monitoring using accuracy benchmarks, human review, drift detection, and cost and latency tracking.
- Embed data quality, governance, privacy, and Responsible AI practices into ingestion and AI pipelines.
- Research and apply data mastering and entity resolution techniques to improve insights from disparate data sources.
- Own production monitoring, incident resolution, continuous improvement, and performance and cost optimization for ingestion and AI pipelines.
- Contribute to the AI & Ingestion community of practice through reusable components, standards, knowledge-sharing sessions, mentoring, and technical reviews.
- Maintain data flow diagrams, data lineage, pipeline runbooks, and prompt and model documentation.
- Partner with product, data science, and business stakeholders to translate requirements into ingestion and AI solutions.
Requirements
- At least 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, including prompt engineering, structured outputs, and evaluation, using services such as Anthropic, OpenAI, or Google Vertex AI/Gemini APIs.
- Experience with cloud data processing, preferably on GCP, including technologies such as BigQuery, Dataflow, Cloud Composer/Airflow, and Vertex AI.
- Experience with web data collection, APIs, SFTP, and other file-delivery channels.
- Familiarity with RAG, embeddings, vector databases, agent frameworks, or MCP is desirable.
- Understanding of AI pipeline engineering practices including MLOps/LLMOps, version control, automated testing, monitoring, and CI/CD.
- Awareness of Responsible AI, data privacy, and data governance considerations such as GDPR.
- Experience with or strong interest in communities of practice, internal technical talks, mentoring, and knowledge sharing.
- Robust data knowledge, preferably involving business datasets, with proven analytical and quantitative skills.
- Fluency in English and languages relevant to the working market where applicable.
- Bachelor’s degree in Data Science, Information Systems, Computer Science, Mathematics, or a similar field.
Categories
AI ApplicationsData Engineering
About Dun & Bradstreet
Dun & Bradstreet builds data and analytics products that help companies assess credit, manage third‑party risk and compliance, and find customers. Its Data Cloud, business credit reports, D‑U‑N‑S Number identity, and APIs are sold as subscriptions and software to finance, procurement, and go‑to‑market teams. Founded in 1841, the company is headquartered in Jacksonville, Florida, and is publicly traded on the NYSE (ticker: DNB).