Description
Summary Senior AI Engineer Needed – Build a Next-Generation Offline AI Assistant Project Overview I am looking for a highly skilled AI Engineer to build a next-generation offline AI assistant that can compete with modern AI systems while running locally on Windows. The goal is to create a fast, intelligent, modular, and scalable assistant that works without depending on cloud AI APIs for its core capabilities. Responsibilities * Design and develop the complete AI architecture. * Build an intelligent conversational assistant with long-term memory. * Integrate local Large Language Models (LLMs) using Ollama. * Implement Retrieval-Augmented Generation (RAG). * Develop a semantic memory system. * Create a plugin architecture for future expansion. * Optimize inference speed and resource usage. * Build a clean and modern desktop application. Required Skills * Python * AI/LLM Development * Ollama * Llama / Qwen / Mistral * RAG * Vector Databases (FAISS, ChromaDB, Milvus, or similar) * LangChain or LlamaIndex * SQLite or PostgreSQL * REST APIs * Windows Desktop Development * Git Core Features * Offline AI assistant * Multi-language support (English, Arabic, Algerian Arabic) * Long-term memory * Knowledge base * File understanding * Intelligent document search * Voice input (Speech-to-Text) * Voice output (Text-to-Speech) * Image understanding * Code generation * Internet search (optional) * Automation capabilities * Plugin support * Multi-agent architecture * High-performance local inference Code Quality The project must follow professional software engineering practices: * Clean architecture * Modular codebase * Well-documented source code * High performance * Easy maintenance * Scalable design * Production-ready quality Long-Term Vision This is not a simple chatbot. The objective is to build a complete AI operating assistant that can continuously evolve with new capabilities over time. I am looking for a developer interested in a long-term collaboration to create a commercial-grade AI product.