I am looking for a hands-on AI Specialist to help optimize and scale an AI-based English fluency coach. The product is already functional, built on an LLM framework, and has been tested with initial users. We are now preparing to scale to 5,000+ users and need to reach a professional, production-grade level. This is not a "build from scratch" project, but an optimization and infrastructure mission. Key Responsibilities: LLM Optimization: Fine-tuning prompts and logic (OpenAI/Anthropic) to ensure high-quality pedagogical feedback, natural conversation flow, and low latency. Memory & Context: Enhancing long-term memory systems (RAG or similar) to allow the bot to track user progress and offer personalized learning paths. Infrastructure & Scaling: Reviewing the current technical setup to ensure stability under high user volume. Cost Efficiency: Optimizing API usage to maintain profitability during scale-up. Requirements: Proven experience with LLM implementation (OpenAI API, Anthropic, etc.). Experience in Prompt Engineering and RAG architectures. Product-oriented mindset (you think about the user experience, not just the code). Fluency in Hebrew is a significant advantage as the initial target market is Hebrew speakers. Project Details: Scope: Project-based with potential for long-term maintenance. Goal: A stable, cost-effective, and high-quality AI coach ready for thousands of users. If you have successfully moved AI products from MVP to production, I’d love to see your portfolio and have a short chat.