Founding Engineer

We are building the system of record for AI-native knowledge work. Nessie auto-syncs AI conversations across every major provider and structures them into queryable, trustworthy context for humans and agents. We are two people. We have years of runway. We are backed by YC, BoxGroup, Pioneer Fund, Precursor, and more.

We are looking for one engineer who can build.

What "build" means here

You have shipped something real. Something with users, or something you use every day because you made it for yourself. You know what it feels like to go from nothing to working software and you have done it more than once.

You are comfortable across the stack. Our codebase is Swift/SwiftUI (macOS app), Go (backend infrastructure), and TypeScript (services). You do not need experience in all of these. You need to be the kind of person who picks up what they need and figures it out.

You reach for AI tools instinctively. You build with Claude Code, Cursor, Codex, or similar - and you are faster because of it. If your first instinct under pressure is to stare at the code instead of giving it to an agent, this is not the right fit.

What you will work on

You will be working at the frontier of AI memory, context retrieval, and knowledge infrastructure. Concretely:

• Cross-platform conversation sync across 7+ AI providers - the hardest unsolved capture problem in the space
• Search and retrieval systems that make thousands of conversations queryable in milliseconds
• Ontology and knowledge structuring - turning messy conversational raw material into trustworthy, typed knowledge
• Agent-facing APIs (CLI, MCP) that let any AI tool access accumulated human reasoning
• The intelligence layer that sits underneath every AI interaction - making agents coherent across sessions, teams, and time

You are building infrastructure for a category that barely exists yet.

What you will NOT need

• A specific degree or school
• Prior startup experience
• A perfect resume
• Permission to try things

What you will need

• The instinct to ship before it is perfect
• The ability to work with extreme autonomy. We are two people. There is no manager. There is no spec. There is a problem and you figure out how to solve it.
• Opinions about products you use. If you have never looked at an app and thought "this is wrong and here is how I would fix it," we are probably not a match.
• Comfort with ambiguity. The product is evolving fast. What you work on in week 1 may be different from week 4. That should excite you, not stress you.

How to apply

Show us something you built. A link to a project, a repo, a product, a tool. If you do not have something to show, build something this week and send it. We care about what you make, not what you say you can make.

Round 1: Show and tell (45 min)

Send us something you built. Before we meet, we will look at your code, your product, your repo - whatever you want to show. On the call, walk us through it: what you built, why, what decisions you made, what you would do differently. We care more about this than your resume.

Round 2: Live build (2 hours)

A real problem from our domain - AI memory and context retrieval. You get full access to AI tools (Claude Code, Cursor, whatever you use), and two hours to build something that works. We are not testing algorithms. We are testing whether you can go from ambiguous problem to working software with good judgment about what to build and what to skip.

Round 3: Paid work trial (1 week)

Work on a real Nessie problem, paid, on your schedule. This is where we both figure out if the fit is real - how you communicate, how you scope, how you handle ambiguity when nobody is watching. We have found this is the only reliable signal for a team this small.