AI was single-player. SuperApp makes it multiplayer.
SuperApp is building the AI collaboration super app—a shared workspace where people and leading AI models think, create, and make decisions together in real time. Instead of splitting communication, AI assistance, and content creation across separate tools, SuperApp brings group messaging, multi-model intelligence, and collaborative creation into one continuous experience.
Teams can move from an initial conversation to a finished document, presentation, spreadsheet, or interactive app without losing the sources, decisions, feedback, and context that shaped the work. SuperApp is multi-provider by design: people can choose, pin, or compare leading models, while the platform can route each step to the capability best suited to the task. (superapp.chat)
Role Overview
We are seeking a visionary systems-minded AI engineer to lead the design, architecture, and development of the Agent Harness. In this role, you will bridge the gap between advanced foundation models (LLMs) and reliable, production-grade execution.
You will not just be "vibe coding" prompts ; you will build the actual state machine, execution sandbox, tool-calling middleware, and security containment layers that allow AI agents to safely execute code, search the web, manipulate files, and query databases in real-time. This is a high-leverage role requiring deep expertise in distributed backend systems, runtime isolation, and stateful agent choreography.