Overview
Do you believe anything is possible? We believe that with the right people and the right data, anything is possible!
Our Mission:
Dun & Bradstreet holds the world’s largest commercial database, with over 600 million records powered by 30,000 data sources updated 5 million times per day. Our teams in Dublin are harnessing the latest technology stacks to build world-class engineering capabilities and develop flexible, scalable solutions through a cloud-first delivery. Each day, we are finding new ways to strengthen our award-winning culture and accelerate creativity, innovation and growth.
Role Overview
We are seeking a highly skilled Senior AI Data Engineer to architect and build scalable data pipelines and infrastructure for AI and Generative AI applications. This role focuses on managing unstructured data, embedding generation, and vector database operations to support advanced AI workflows such as Retrieval-Augmented Generation (RAG), semantic search, and agentic systems.
You will work closely with AI engineers, data scientists, and platform architects to deliver high-performance, secure, and resilient data systems that power enterprise-grade AI solutions.
Responsibilities
* Design and implement ETL/ELT pipelines for structured and unstructured data, optimized for embedding generation and vector indexing.
* Build and maintain embedding pipelines using OpenAI, Hugging Face, or Vertex AI models
* Develop and manage vector databases for semantic search and similarity matching.
* Integrate metadata-aware filtering and real-time upserts for contextual and dynamic querying.
* Collaborate with platform teams to ensure secure provisioning, RBAC, encryption, and compliance with data governance policies.
* Optimize performance using GPU acceleration, tiered storage, and ANN indexing algorithms.
* Support observability, monitoring, and incident response for data pipelines and vector infrastructure.
* Contribute to the AIBE Data Hub and RAG-as-a-Service initiatives.
Qualifications
* Bachelor’s or master’s degree in computer science, Data Engineering, or related field.
* 8+ years of experience in data engineering, with at least 3 years managing unstructured data and embedding pipelines
* Strong proficiency in Python, and data pipeline tools (Dataflow, Pub/Sub, Cloud Functions, Cloud Storage, Apache beam, Air Flow, Vertex AI Pipelines, Kafka, Flink).
* Experience with embedding models and vector search platforms (e.g., BigQuery Vector Search, QDRANT)
* Deep understanding of unstructured data processing, especially text, PDFs, etc.
* Familiarity with cloud platforms (Azure, GCP, AWS) and services like Databricks, Vertex AI, and Dataflow.
* Knowledge of containerization and microservices (Docker, Kubernetes).
* Experience with CI/CD pipelines, Terraform, and DevSecOps practices.
Desirable Experience
* Hands-on experience with hybrid search and agentic workflows.
* Familiarity with multimodal analytics and joining structured/unstructured data for advanced use cases.
* Contributions to platform-level services such as RAG-as-a-Service and embedding generation frameworks.
What’s on offer at D&B (Ireland specific)
* 25 days annual leave (plus 2 paid volunteer days & 1 paid un-sick day)
* Holiday buy & sell (the option to buy or sell up to 5 additional days per year)
* Flexible working - hybrid model
* Employee Health Insurance
* Mental Health Support program
* Pension Contribution
* Family Friendly Leave (Maternity, Paternity, Parental, Marriage and Bereavement)
* Life Assurance
* Educational Assistance Program
* Life-Style Account (D&B will match your contributions up to €40 per month and can be used to claim for a range of health-related, leisure or lifestyle activities)
Additional
All employees and contractors working in D&B should be aware that they have responsibilities in relation to the Company’s Business Management System. This relates to information and its security, quality, environment and health and safety both during and post-employment with D&B
Dun & Bradstreet is an Equal Opportunity Employer
#J-18808-Ljbffr