We’re looking for an intern who can build. You’ll work directly with the founders on the shared context layer for recursive companies: a data lake that ingests everything a team produces with AI, an ontology that turns it into trustworthy, typed knowledge, and the loop that lets people and agents improve from it.

This is not a sandbox project. We’re two people, so you will own a real piece of the product, ship it to real users, and see how they use it. You’ll get a scoped project in week one. By the end, the work you shipped will be live in production.

What "build" means here

• You have shipped something real: a side project, a hackathon build that people actually used, a tool you made for yourself and still use every day. You’ve gone from nothing to working software at least once.
• You are comfortable learning a new stack quickly. We ship native desktop apps on macOS, Windows, and Linux, a CLI and background daemon, agent integrations, and a cloud backend, across several languages. You don’t need experience in all of these. You do need to pick things up fast.
• You reach for AI tools instinctively (Claude Code, Cursor, Codex) and you’re faster because of it. If your first instinct under pressure is to stare at the code instead of handing it to an agent, this isn’t the right fit.

What you might work on

You’ll own one or two of these, scoped to what you can ship during the internship:

• Ingestion: a new source connector, from AI chat apps and coding agents to meeting recorders, notes apps, and email. Cross-provider capture is still the hardest unsolved problem in the space.
• Search and retrieval: making thousands of sessions and documents queryable in milliseconds, across local and cloud.
• Self-improving agents: measuring skill invocations, mining agent traces for failures and repeated workflows, and proposing reviewable edits back to a team’s skills.
• Agent-facing surfaces: our CLI, MCP connector, and plugins, so any AI tool can reach a team’s accumulated context.
• Ontology: derived fields, conflict resolution, and keeping the live state of a company current as new work flows in.
• Product polish: the user experience, from first launch through the features people use every day.

What you will NOT need

• A specific degree, major, or school
• A prior internship
• A perfect resume
• Permission to try things

What you will need

• The instinct to ship before it’s perfect
• Autonomy. You’ll get context, feedback, and fast answers from the founders, but no one will hand you a detailed spec. You get a problem and you figure out how to solve it.
• Opinions about the products you use. If you’ve never looked at an app and thought “this is wrong and here’s how I’d fix it,” we’re probably not a match.
• Comfort with ambiguity. The product moves fast, and what matters in week 1 may differ from week 6. That should excite you.

What we offer

• $4K–$8K per month
• Expensed meals in office
• Flight stipend to come to SF
• Daily work alongside the founders, with code review and mentorship on everything you ship
• A clear path to a full-time offer for interns who do great work

About Nessie

Knowledge work is being restructured by AI. Strategy happens in Claude. Research happens in ChatGPT. Building happens in Claude Code and Codex. Meetings get recorded, notes get written, agents run for hours and leave behind traces nobody reads. The people defining the next decade of work are already thinking with AI every day. But none of that thinking compounds. Every session starts from zero. The reasoning behind decisions, the context behind strategies, the evolution of ideas across hundreds of conversations: all of it evaporates.

Nessie is the infrastructure that makes it permanent. We auto-sync AI conversations and agent traces across every major provider (ChatGPT, Claude, Gemini, Perplexity, Claude Code, Codex, Cursor, OpenClaw, Hermes, and more) alongside meetings, notes, and email from tools like Granola, Read AI, Plaud, and Obsidian. Everything a team produces with AI flows into one place and compounds over time.

Nessie turns that raw, heterogeneous data into an ontology: the live state of a company. Not a static schema but a continuously updated record of what the company knows, what it has decided, who owns what, and how its thinking has evolved, kept current as new work flows in. It is queryable from any agent through our CLI, MCP connector, and plugins, shareable across a team with real permissions, and deployable on-prem for organizations that need it.

Then the loop closes. Once a company’s state is legible to its agents, every agent run becomes training signal: which skills worked, which failed, which workflows keep repeating. Nessie feeds that signal back as reviewable improvements to the skills, prompts, and processes the team runs on. This is what makes a company recursive: its agents get better from its own history, the people working with them get better too, and the compounding never stops.

Founded by two Yale CS grads and former Amazon engineers in San Francisco. Backed by BoxGroup, Pioneer Fund, Y Combinator, Precursor, and more.