Associate Data Engineer, Enterprise Data Engineering

At the World Bank, a member of the World Bank Group (WBG), you’ll join a diverse, global community working across cultures, disciplines, and borders to address the world’s most pressing development challenges. With 1.2 billion young people reaching working age in the decade ahead, the challenge of job creation has never been greater. Through partnerships across 145 countries and more than 182 offices worldwide, we work with governments, private sector, development partners and other stakeholders to invest in people, strengthen markets, and deliver scalable, data-driven solutions that generate more and better jobs and improve lives. For more information, visit https://www.worldbank.org/en/who-we-are/ibrd ITS Vice Presidency Context The Information and Technology Solutions (ITS) Vice Presidential Unit (VPU) enables the World Bank Group to achieve its mission of ending extreme poverty and boost shared prosperity on a livable planet by delivering transformative information and technologies to its staff working in over 150+ locations. For more information on ITS, see this video: https://www.youtube.com/watch?reload=9 v=VTFGffa1Y7w Unit Context: The ITS Data Office (ITSDO) is the central entity within the World Bank Group’s Information and Technology Solutions (ITS) department responsible for enabling data, AI, information, and knowledge capabilities across the institution. It comprises four Units focused on platforms tools, product service delivery, enablement and governance. The office plays a pivotal role in advancing the Bank’s digital transformation, supporting business domains with trusted data, information and AI capabilities, and fostering a culture of responsible innovation. The Platforms Tools Unit is responsible for building, integrating, and continuously modernizing the foundational technology infrastructure that powers data, AI, archives, and knowledge services across the World Bank Group. The unit leads the rationalization and simplification of legacy systems, and modernization towards platforms that are scalable, secure, interoperable, and designed for self-service and adoption. The unit plays a critical role in enabling enterprise-wide transformation by delivering data environments, digitization infrastructure, and open knowledge repositories that are AI-ready and aligned with business needs. Duties and accountabilities: RAG Unstructured Data Pipelines

• Design and build scalable ingestion and processing pipelines for unstructured content including PDFs, audio, video, and images.
• Implement document processing workflows covering OCR, metadata extraction, content enrichment, chunking strategies, and vector indexing to support RAG solutions.
• Develop multimodal processing capabilities that handle diverse source formats consistently and at scale.
• Build and maintain embedding, retrieval, and re-ranking pipelines integrated with enterprise search and AI platforms. Reusable Patterns Accelerators
• Develop a library of reusable pipeline templates, blueprints, and starter kits for common unstructured data processing use cases.
• Build Infrastructure as Code (IaC) patterns and standardized deployment configurations that domain teams can adopt independently.
• Document reference architectures, cookbooks, and implementation guides to reduce time-to-value across teams. Collaboration
• Partner with data architects, AI engineers, and business teams to translate requirements into reliable data products.
• Contribute to code reviews, engineering standards, and shared documentation practices.