Description
We are seeking an experienced full-stack AI engineer for a focused, short-term contract to implement, optimize, and deploy a real-time chatbot interface within our existing AI-native web and mobile applications. Project Scope Our platform utilizes a robust local and cloud-based LLM inference setup. We need to bridge the gap between our backend inference layer and the user interface. Your primary task will be to integrate a streaming-first chatbot component into both our React/Next.js web platform and our mobile client, ensuring a cohesive user experience across both targets. Key Responsibilities Chatbot Integration: Implement and refine a responsive chatbot UI that handles real-time token streaming, message history, and local state management. Data & Auth Binding: Connect the chat interface with our existing backend database and authentication layers (Supabase, Prisma, Stytch). Inference Optimization: Interface with our local/hosted LLM streaming APIs (handling Server-Sent Events/SSE) to ensure low-latency UI rendering and graceful error handling. Deployment: Update, test, and deploy the updated application to production web and staging mobile environments, ensuring the build runs smoothly without breaking existing features. Required Technical Stack Frontend/Mobile: React, Next.js, Tailwind CSS, and experience with cross-platform mobile deployments (iOS/Android). LLM Inference & Deployment: Deep understanding of streaming APIs, token handling, and frontend latency optimizatio