AI Developer – PDF Search & Business Rule Extraction

OpenBean Inc. is seeking an experienced AI/LLM Developer to build a system that can intelligently search and extract business rules from a large corpus of PDF documents. The ideal candidate will have strong skills in Python, NLP/LLMs, document processing, and machine learning, and be capable of building end-to-end solutions using modern AI toolchains.

Responsibilities:

• Develop a solution to ingest and index hundreds of PDF files.
• Build a natural language search interface powered by a Large Language Model (LLM).
• Enable the system to infer, extract, and summarize business rules from PDF text.
• Fine-tune or prompt-engineer LLMs (e.g., OpenAI, Mistral, Claude, or open-source like LLaMA) for domain-specific rule extraction.
• Implement techniques for semantic search, embedding generation, and retrieval-augmented generation (RAG).
• Work with vector databases (e.g., Pinecone, FAISS, Chroma) for efficient search.
• Design and implement APIs or a UI interface for querying and visualizing results.
• Ensure proper handling of scanned PDFs using OCR if needed (e.g., Tesseract, Amazon Textract)

Skills Required:

• Strong Python programming skills.
• Experience with LLMs (OpenAI, HuggingFace, LangChain, LlamaIndex).
• Proficient in PDF processing libraries (e.g., PyMuPDF, PDFPlumber, or Adobe APIs).
• Knowledge of text embeddings, vector search, and similarity matching.
• Familiarity with document classification and information extraction.
• Experience with cloud services (AWS/GCP/Azure) is a plus.
• Strong problem-solving, communication, and documentation skills.