Member of Technical Staff

Capy•San Francisco, CA

1d•$200,000 - $300,000•Onsite

About The Position

We're building the AI software engineer you hand real work to. A thread starts from Slack, Linear, the web app, the desktop app, or the API; Capy makes the change on a cloud machine or right on your own laptop, office Mac mini, or any device you've paired, opens the pull request, and handles CI and review feedback until it merges. Work moves between your devices and the cloud mid-thread, big work splits into parallel agents across those machines, a review agent reads every PR, and automations run on a schedule or on platform events. The age of the solo coder is over: developers stop babysitting single agent sessions and start orchestrating fleets of agents, together with their team. We're a small team in San Francisco, backed by Y Combinator and tier-1 investors, shipping to teams that run Capy on production codebases every day. We build Capy with Capy: our own PRs, reviews, and automations run through it. AI coding is a crowded market now, and developers expect first-minute magic and a quality bar that holds across every surface. Meeting that bar means you will have to own the entire product experience and craft it with care. "Full stack" here means the whole width of Capy: the interfaces developers direct agents from, the agent loop and its tools, the backend the loop re-plans from, the infrastructure the machines boot on, and the layer that talks to every frontier model. You'll make product decisions without a PM, design without waiting on a mockup, and solve the hard engineering problem yourself rather than handing it off. This is a role for people who build with taste and feel the gap between what exists and what should, then close it.

Requirements

Agent-native. Claude Code, Codex, Cursor, etc (or your own harness) is how you already work, and you have sharp opinions about where they fall short.
Fluent in our stack. TypeScript 7 on Node 24 and React in production, and typed functional code (Effect or the like) you can read and write without a ramp. You've shipped against MySQL, run something on Kubernetes, and touched a message bus like NATS.
Comfortable at every layer. A slow query, a broken websocket, a failing Helm release, and a misbehaving tool call in the same afternoon, and you don't wait for a specialist on any of them.
Taste in interfaces. You notice the four-pixel misalignment, you care about motion, hierarchy, and empty states, and you can point at shipped work that proves it.
Independent product judgment. You make the call on what to build and how it should feel without a PM or designer defining the problem first.
Fast without shortcuts. You verify your work, read your diffs, and would rather delete code than add an abstraction nobody uses yet.
In San Francisco. In a room with people doing the same.

Nice To Haves

Effect in production, or Rust (our remote desktop is Rust).
Sandboxed execution, VM images, remote desktops, or a git proxy you've built or operated.
A model-provider layer you've built, or direct work against Anthropic, OpenAI, and Gemini APIs.
Design-tool fluency (Figma or similar) on top of prototyping in code.
Public work: open source, posts, demos, an active account on X.
Founder or early-employee experience.

Responsibilities

Ship across the whole stack. One day is a new tool in the agent loop, the next is the React surface that shows what it did, the migration behind it, and the Kubernetes change that ships it.
Set the standard for agent UX. Threads, tasks, diffs, reviews, live machine desktops streamed from our Rust remote desktop: twenty-five agents running at once need an interface that stays legible.
Design in code. Take a feature from rough idea to a polished, animated, keyboard-first interface in the React web app and Electron desktop app.
Build the backend the agent runs on. Effect services over MySQL (Vitess on PlanetScale), realtime fan-out over NATS, the typed API and protocol every client shares, the git proxy, the worker that drains threads.
Push what the agent can do. New tools, better verification, tighter loops with CI and review, smarter task orchestration, and the provider layer across Anthropic, OpenAI, Gemini, and the rest.
Run the infrastructure. The Kubernetes clusters and IaC that deploy Capy, and the VM images and sandbox platform every cloud machine boots from.
Direct Capy on Capy. Most of your day is writing specs, steering agents, reviewing their PRs, and fixing the harness when it lets them down.
Talk to users. Developers running Capy on real codebases tell you what's wrong; you turn it into what ships that day.