The opportunity

Every tool you use was built as an island, so you became the glue between them: a name from one app into the CRM, a time from the CRM into your calendar, a note from the calendar into a doc. AI showed up and mostly became an eleventh window to paste into.

We're building a hybrid of AI and software standing on one shared brain. It holds your context and hands you real software built on top of it - so an ordinary scheduling tool becomes one that writes the invite itself and knows which of your busy hours bend, and for whom. Software for the path you repeat, AI for the edge that never repeats.

We're a 15-person team backed by top-tier VCs, having raised a $30M seed - the largest in our accelerator's history. We work from an office in San Francisco's Presidio, fifty metres from Crissy Field beach, and we work hard because we can see and feel the outcome every day.

The role

You'll write and ship full-stack features end to end, from the agent runtime and backend APIs to the web and desktop UI that users interact with every day.

We're still ~20 people and shipping to our first paying users. You won't just be building features - you'll be making the decisions that determine whether this system holds at 1000x the current load.

What you'll do

You'll work directly with our CTO. Examples of what you might work on:

Sandbox infrastructure - build and operate the environment where agents execute code: process isolation, resource limits, secure credential handling across thousands of concurrent sessions.
Deployment & migration - design the pipeline for a Cloudflare Workers + Fly.io architecture, including blue-green rollouts and canary patterns.
Real-time systems - instrument workloads end to end: SSE streaming, task queues, and multi-model LLM provider routing.
New capabilities - ship backend features (tool integrations, scheduled task execution, memory indexing) and see them used by real people the same week.
Operational excellence - reduce toil for a small team with structured logging, tracing, monitoring, and incident response tooling that actually works at scale.
Plus whatever you see that needs building.

Stack: TypeScript, Cloudflare Workers, Durable Objects, Hono, Drizzle ORM, Postgres, Zod, SST, Vercel AI SDK, Docker, React, Vite

What we're looking for

Minimum:

5+ years of engineering experience building and operating backend systems in production. You've been on-call.
Fluent in TypeScript and comfortable working across the stack, but your instinct is to go deeper on the backend.
You've built real-time systems: WebSockets, SSE, event streaming, or message queues in production.
Distributed systems intuition - you understand consistency tradeoffs and have opinions about them.
You've shipped infrastructure to real users, not just internal tooling.

Bonus (not required):

Experience with Cloudflare Workers, Durable Objects, or serverless compute at the edge.
You've built agent systems, model routing layers, or tool-use architectures with LLMs.
You've been a founder or early-stage engineer and care deeply about product.

Logistics

Location: San Francisco (Presidio) - in-person, 5 days a week in the office.
You must be based in the Bay Area or willing to relocate before starting.
US work authorisation required; open to O-1 or J-1 visa sponsorship for exceptional candidates.
Compensation: $180K-$240K base + meaningful early-stage equity, plus health, dental, 401(k), considerable PTO, gym budget, and lunch.

Our process

We keep it simple. Exceptional candidates go from first touch to offer within 2 weeks.

Application - submit your resume and answer a few short questions.
TechTree screening
15-minute intro call - align on location, motivation, and logistics.
45-minute technical interview - work through a real backend problem.
System design interview - a deep dive into how you'd architect a real problem we've faced.
Final conversation - we answer your questions and scope the work trial.
Work trial - a paid trial on a real project in person, usually a few days to two weeks.