This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Capstone IT is helping our client to hire a Senior Developer with strong Python and data engineering experience to support a large-scale AI and archival modernization initiative. This role will focus on processing unstructured data, developing AI-powered search and classification capabilities, and building scalable solutions for millions of archived documents.
Job Responsibility:
Design and maintain scalable Python and SQL data pipelines
Process and organize large volumes of unstructured data including PDFs, images, scanned files, and documents
Utilize OCR technologies to extract searchable text and metadata from files
Build and support AI-powered agents, intelligent search, and document classification solutions
Assist with RAG pipelines, embeddings, and vector-based search capabilities
Support metadata management and governance across archival repositories including SharePoint, DFS, and Preservica
Integrate data from platforms such as Hexagon, Bentley, and Autodesk Construction Cloud (ACC)
Collaborate with cross-functional teams to improve enterprise data accessibility and efficiency
Requirements:
Bachelor's degree in Computer Science, Data Analytics, MIS, or related field
8+ years of software development or data engineering experience
Strong experience with Python and SQL development
Experience working with unstructured data and OCR technologies
Experience building APIs and working with tools such as Postman
Understanding of metadata management, tagging, and classification concepts
Exposure to AI/ML, AI agents, embeddings, vector stores, or Generative AI solutions
Experience with .NET/C# and/or JavaScript
Nice to have:
Experience within the Architecture, Engineering, and Construction (AEC) industry
Familiarity with Hexagon, Bentley, or Autodesk Construction Cloud (ACC)