Dex is Cursor for everyday operations.

We’re reimagining the browser as an intelligent workspace—one that understands what you’re doing and helps you do it faster. Instead of static pages and disconnected apps, Dex adds a layer of context-aware AI that works with you in real time.

We’re a small, fast-moving team, with 7-figure backing from top-tier investors, solving one of the most fundamental problems in computing: how humans and computers work together.

We're creating the third layer of interaction — a personalized AI action layer that lives across all your workflows. If that excites you, and you’re a world-class infrastructure expert, please apply.

Why Dex Matters

• Flow is everything. Every tab switch, every UI reload, every wait for an AI handoff kills momentum. 
• The future of productivity is collaborative AI. Dex is an active, real-time partner embedded directly in your browser—the place where your work actually lives.
• Context makes or breaks a product. You need systems that understand where you are, what you're doing, and what should happen next.

What You'll Build

• Core agent components, including memory stores, context compression, inter-agent protocols, planning and tool use.
• High performance state management and real-time UI observation systems.
• Scalable infrastructure for browser-native AI.

Requirements

• Expert in React/Next.js, TypeScript, and Python.
• Deep browser internals experience.
• Proven rapid prototype to production track record.
• Preferred: Prior experience with AI/ML infra or agentic systems.

Sample Projects

• Translating browser inputs (voice, keyboard and mouse inputs, tab changes, DOM) into actionable workflow graphs.
• Agentic systems that predict and execute users’ next steps in complex workflows.
• A searchable, self-updating memory store for personalized user flow paths.

Existing approaches—like computer-use data and Model Context Protocols—still overlook a fundamental element: a deep understanding of how individuals actually use software.

Every person navigates their workday with unique mental models and personal systems for interacting with platforms and staying organized. These invisible frameworks shape productivity and workflow in ways that generic data can’t capture.

How can we systematically capture, structure, and teach these personal workflows to AI—enabling it to become a truly proactive, personalized extension of each user?