AI Automation Engineer

We’re looking for an experienced AI automation engineer to design and build an end-to-end pipeline that takes incoming documents, extracts the information we need, and coordinates actions across our tools with minimal manual work. What the automation needs to do: Ingest documents from images, PDFs or similar Run OCR on scanned and image-based files, including Arabic and English text / handwriting / tables, with high accuracy. Extract structured data using LLMs and/or document AI, and validate it against business rules. Coordinate tools and systems: push extracted data into portals, trigger follow-up actions, and pass context between steps. Handle exceptions: flag low-confidence results for human review instead of failing silently. Log and monitor each run so we can audit what happened and spot errors. Deliverables: A working, deployed automation pipeline Clear documentation (architecture, setup, how to maintain it) A handover session or short walkthrough video weeks of post-launch support for bug fixes Required skills: Proven experience building production AI or LLM-based automations OCR and document AI (e.g., Tesseract, Google Document AI, AWS Textract, Azure Document Intelligence) LLM APIs and structured extraction (Claude, OpenAI or similar), plus prompt design Agent and tool orchestration (function calling, LangChain/LangGraph, MCP, or custom) Workflow automation platforms (n8n, Make, Zapier) and/or Python API integrations, webhooks, and error handling Nice to have: Experience with Arabic OCR Human-in-the-loop review interfaces Cloud deployment (AWS, GCP, Azure) and data privacy best practices To apply, please include: One or two similar automations you’ve built: what they did and what results they delivered Which stack you’d propose for this project and why A rough timeline and cost estimate Start your proposal with the word “PIPELINE” so we know you read the full post