Senior Platform Engineer

Sauna•San Francisco, CA

22d•$180,000 - $240,000•Onsite

About The Position

Sauna's agent runtime has to keep track of work when a tool fails or new code ships mid-task. One session might start with a message, check Calendar, draft a Slack reply, and update Linear after the first response. A tool call can time out after the action succeeds; the runtime needs to know what happened before retrying. You'll build the execution engine behind those sessions, choosing when work belongs in an actor and when a job is enough. You'll also design how long-running processes deploy while other tasks are in flight. This is a senior, hands-on engineering role. You'll make those calls with the team, write the code, and own it in production. We'll teach you our agent harness.

Requirements

You've built and operated stateful backend systems in production, including work that outlasts the request that started it.
You can explain a decision you made between an actor, a background job, or a simpler service, and show what you shipped.
You've debugged concurrency, retries, or recovery in code you've owned.
You're productive in TypeScript and want to keep writing code as your scope grows.
US work authorisation

Nice To Haves

You've worked on an agent runtime or agent harness.
You've worked with Cloudflare Workers, Durable Objects, or another actor-based runtime.
You've deployed long-running processes that persist or resume work across a code release.

Responsibilities

Build and improve the runtime that starts agent work, carries session state through tool calls, and resumes interrupted runs.
Choose between actors and jobs for different kinds of work. Implement the choice and check how it behaves when sessions overlap.
Design how long-running processes drain or resume when code changes, keeping in-flight work accounted for across releases.
Handle retries and timeouts around tool calls, including cases where an external action succeeded but the response never came back.
Make runtime failures traceable. Find why a run stopped or stalled, fix the execution path, and see the change through to production.