We’re building a real-time, intelligent chatbot system that goes beyond traditional prompt-response behavior — something dynamic, contextual, and production-ready.

We're looking for a senior full-stack AI engineer who can lead the development of a real-time chatbot powered by LLMs, integrated with a web-based frontend, and capable of handling live user input with minimal latency. You’ll be working directly with the product owner and designer to create a polished, performant conversational platform.

What You’ll Build:

-A real-time chatbot experience using OpenAI / Anthropic APIs (or custom LLMs)
-Frontend using React / Next.js with a focus on UX, speed, and responsiveness
-Backend in Node.js / Python (FastAPI) for orchestrating LLMs, memory, and API calls
-State management for context-aware conversations (via RAG, embeddings, or vector DB)
-Scalable architecture with Docker, WebSockets, and deployment to AWS/GCP/Vercel

We move fast, iterate weekly, and are building something with real traction. If you’re an engineer who thinks in systems and sweats the UX, we’d love to hear from you.