We are looking for a full-time Developer with strong experience in building intelligent tools and workflows powered by AI, automation, and document processing technologies. You will work on a range of projects involving natural language processing (NLP), LLM integration, PDF and document automation, and multilingual content handling. The ideal candidate is skilled in modern AI tooling, with a solid understanding of vector databases, token optimization for large language models (LLMs), and system integration. This is a long-term opportunity for someone who thrives in technically dynamic environments and can contribute to both current and future AI-driven development initiatives. Role & responsibilities Design and develop modular, scalable tools leveraging AI and automation Integrate document parsing, language translation, and structured data extraction Optimize prompts and payloads for efficient LLM use (minimizing token usage) Use vector databases for document search, retrieval, and contextual enhancement Build pipelines that combine NLP, document generation, and workflow orchestration Automate repetitive data and content processing tasks across languages and formats Collaborate on architecture decisions, best practices, and code reviews Write clean, maintainable, and well-documented code Preferred candidate profile Core Development: Strong programming experience in Python RESTful API development and integration Familiarity with containerization (e.g., Docker) AI & NLP Tooling: Experience using LLMs (OpenAI, Hugging Face Transformers, etc.) Translation APIs: Google, DeepL, Azure, Hugging Face models Orchestration tools like LangChain, LlamaIndex, or similar Prompt engineering and token optimization for LLMs Experience with Vector Databases such as FAISS, Pinecone,Weaviate, or Chroma Document Processing: Libraries: PyMuPDF, pdfminer.six, pdfplumber PDF generation tools: ReportLab, WeasyPrint, or HTML-to-PDF tools RTL and multilingual support: python-bidi, arabic-reshaper, Unicode handling Bonus Skills (Nice to Have): Knowledge of data analytics, data science, or machine learning Familiarity with OCR tools (Tesseract, Google Vision, etc.) Knowledge of agentic AI frameworks (LangGraph, AutoGen, CrewAI) Cloud deployment experience (AWS, GCP, or Azure) Experience handling structured documents (e.g., tables, forms, templates)