Engineer in Residence, AICoS

Managers with heavy meeting loads spend hours translating conversations into decisions, action items, owners, and follow-ups. The tools record what happened, but they rarely close the loop across projects and people. This role is to build an AI chief of staff that turns meeting context into structured work, routes it correctly, and keeps commitments moving without creating another system for managers to maintain.

• A meeting intake and extraction pipeline that identifies decisions, action items, owners, deadlines, and unresolved questions.
• A routing engine that maps work to the right project, person, and operating context.
• A review and follow-up system that drafts nudges, prepares one-on-ones, and keeps action items current.
• A lightweight work graph and integration layer across tools such as Slack, Asana, Notion, Google Workspace, and calendars.

• →Own the product across meeting ingestion, structured extraction, routing, manager review, integrations, and deployment.
• →Design the context model that connects people, projects, decisions, and commitments without requiring heavy setup.
• →Build evals and guardrails for extraction quality, incorrect routing, duplicate tasks, and unhelpful follow-ups.
• →Test the single-player manager workflow quickly and learn which parts create enough daily value before team adoption.
• →Work with AI Fund's build team on product scope, technical risk, and the path from manager utility to a broader operating system.

• Strong full-stack or backend engineering ability across workflow products, APIs, data models, and production integrations.
• Demonstrated experience building GenAI systems for structured extraction, agentic workflows, tool use, evals, and guardrails.
• Experience integrating workplace tools, task systems, calendars, messaging products, or document platforms.
• Product judgment for human-in-the-loop automation where managers can review important decisions without becoming the system's full-time operator.
• You know how to use AI coding assistants and modern AI tools to accelerate implementation without surrendering engineering judgment.
• US work authorization. We are unable to sponsor visas for this role.

Experience with meeting transcription, audio pipelines, or calendar intelligence.

Experience building productivity, project-management, or collaboration software.

Founder or founding engineer experience shipping a workflow product from zero to one.

A builder who is impatient with coordination work that software should already handle.

Someone who can make an AI workflow feel dependable enough to become part of a manager's daily operating rhythm.

• This is a 12-week, full-time, on-site residency in Mountain View, California.
• Not every residency becomes a company. The goal is to pressure-test the idea quickly and honestly with real users and customers.
• You will be building an AI Fund idea, not bringing your own startup idea into the program.
• The process typically includes a Builder Event or equivalent working conversation, then a 48-hour Builder Challenge, then panel review with AI Fund build leadership.
• The compensation is intentionally modest during the residency because the upside, if the idea works, is a founder-level role.