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).
You will build AI-powered automation for operational workflows that are currently manual and slow. The first mission is inventory processing: tenants move out, inventories are completed (photos, comments, documents), and today a human reviews every one to assess damage, estimate costs, and decide what to deduct from the deposit. You will automate that end-to-end.
Job Responsibility:
Build AI-powered automation for operational workflows
Ingest inventory documents and extract structured damage assessments using vision and language models
Compare move-out inventories against move-in inventories to identify new damage and attribute responsibility
Estimate repair costs based on damage type, severity, and historical data
Feed results into the deposit return process
Build this as a reusable document processing pipeline
Requirements:
Built LLM-powered applications in production
Strong in Python and comfortable with frameworks like LlamaIndex, LangChain, or equivalent orchestration tools
Experience with vision models and multimodal AI
Understand how to design evaluation and feedback loops for AI systems
Can work with APIs, databases (Postgres), and existing internal systems
Use AI tools (Copilot, Claude, Cursor, etc.) as part of daily workflow
Have worked in fast-moving environments
Can talk to non-technical operations teams
Comfortable with ambiguity and have a bias for action
Have a proven track record of AI-powered systems built that run in production