AI Data Engineer for RAG Knowledge Base Processing:

We are looking for an experienced Python Data Engineer to build a data transformation pipeline that converts raw German technical content into a clean, English, RAG-ready knowledge base. Responsibilities: Clean and sanitize raw text while preserving critical technical information. Translate German technical content into accurate English using DeepL or LLMs. Extract and organize content from PDFs, images, and engineering documents. Generate metadata and summaries for visual assets using Vision LLMs (GPT-4o, Claude, etc.). Convert processed content into Markdown with YAML front matter. Merge documents into structured domain logbooks optimized for RAG ingestion. Requirements: Strong Python skills (text processing, regex, JSON, automation). Experience with PDF/OCR tools (Docling, Unstructured, OCRmyPDF, or similar). Hands-on experience with LLMs, Vision AI, and translation APIs. Good understanding of RAG pipelines, metadata management, and document chunking. If you have experience building AI-ready data pipelines and knowledge base processing systems, we'd love to hear from you.