Data Management & Governance - Oversee metadata management and enrichment for key data repositories including SharePoint, Distributed File Systems (DFS), and Preservica. - Design and lead execution of technical implementation strategy of data governance and compliance for archived project data/content. - Administer data archiving and retention policies to ensure data integrity and compliance. - Implement classification frameworks to support Role-Based Access Control (RBAC) and Attribute-Based Access Control (ABAC). Data Engineering & Integration - Design, build, and maintain optimized data pipelines using SQL and Python. - Integrate various engineering and project execution data sources (including Hexagon, Bentley, and Autodesk Construction Cloud), harmonizing and tagging metadata to create unified data products. - Collaborate with domain teams to identify, extract, and organize data for analysis and product development. - Utilize Optical Character Recognition (OCR) to extract structured data from unstructured sources at scale. Agentic AI - Build and maintain Retrieval-Augmented Generation (RAG) pipelines for content classification. - Develop and own the technical experience of the archive and classification agents. - Construct and evaluate Generative AI agents, ensuring output quality, safety, reliability, and grounded ness using established evaluation frameworks." ][ "Job Requirements:\r\n\r\n - Bachelor Degree in Computer Science, Management Information Systems, Data Analytics, or related field and 8 years' experience\r\n\r\n - Expert knowledge in programming languages and coding principles and procedures. \r\n\r\n - Proficiency in Python, .NET/ C#, or JavaScript.\r\n\r\n - Extensive experience with API development and tools like Postman.\r\n\r\n - Demonstrated experience in building and maintaining data pipelines with SQL and Python.\r\n\r\n - Strong understanding of machine-readable metadata standards and taxonomies.\r\n\r\n - Experience building, evaluating, and maintaining AI/ ML models and agents.\r\n\r\n - Experience developing embeddings or vector stores on unstructured content." ]