Summer 2026 Full-Stack Engineer Intern

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 looking for engineers who can turn research prototypes into production-ready systems. You'll work at the intersection of browser automation, agent infrastructure, and intuitive UX that make complex agent behavior understandable and controllable.

Preferred: History of high-achieving projects/work experience, open source contributions, or competitive math/cs/physics experience.

• Full-stack browser extension interfaces based on research prototypes.
• End-to-end features using React/Next.js, Python, and SQL.
• Design intuitive interfaces for how users should delegate and override AI actions.
• iMessage, communications channels, desktop-native, wearables integrations

• Strong foundation in React/Next.js and TypeScript.
• Experience building and shipping complex web apps and/or browser extensions.
• Familiarity with design systems like Figma
• Preferred: Proof of meaningful open-source contribution.
• Preferred: Strong UI/UX or design portfolio.

• Reusable tool call and output components for LLM-generated responses.
• Building efficient indexing, search, and memory layer architecture.
• Developing security and guardrails to approve and deny agent requests.
• Integrating third-party platforms (e.g. Slack, Notion, Gmail) to enable workflows.

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?