Staff Engineer

Wordware•San Francisco, CA

3d•$280,000 - $400,000•Onsite

About The Position

You've seen what happens when systems hit scale, and you know which parts to rebuild before they break. This isn't a management role. You're the most experienced builder on the team, and the CTO's partner on every architectural decision that matters. Sauna's architecture works today. It won't be optimal at 1000x the current load with 50x the integration surface. You'll make the calls that shape what it becomes. Here are a few examples: Make hard architectural tradeoffs and own the outcome: Durable Object SQLite vs. shared Postgres for session state. Cloudflare Workers CPU limits vs. longer-running workloads. Single-tenant sandboxes vs. multi-tenant pools. You decide, you migrate, you ship. Design the system that handles concurrent agent sessions across integrations, an agent responding to an iMessage, checking Calendar, drafting a Slack reply, and updating Linear, all within one session with consistent state. Define reliability and observability standards for a ~15-person team: SLOs, error budgets, tracing strategy, incident response patterns that actually work at our scale. Review every significant PR. Set technical direction without blocking velocity. Your pattern recognition from prior scale experience is the product. Ship code daily. Architectural leadership without output is a consulting engagement, not a job. $your ideas}.

Requirements

You have 8+ years as an IC engineer. You've been Staff or Principal at a company with real scale, but you left (or want to leave) because you want to build, not attend architecture review meetings.
You've built and operated systems that serve millions of users. You know the failure modes of distributed state, real-time streaming, and multi-tenant isolation, not from papers, from production.
You have recent, hands-on AI/LLM work. You've built agent systems, model routing layers, or tool-use architectures. You understand why tool execution in an agentic loop is fundamentally different from request-response.
You're fluent in TypeScript and productive in it on day one. The entire stack is TypeScript.
You've left a comfortable role because the work stopped being interesting. You want real ownership and real risk.

Nice To Haves

You have strong opinions on agent runtimes (Durable Objects vs. actors vs. microservices) and deployment strategies for long-running processes.
You've worked with Cloudflare Workers at scale.
You've contributed to or maintained significant open source projects.

Responsibilities

Make hard architectural tradeoffs and own the outcome: Durable Object SQLite vs. shared Postgres for session state. Cloudflare Workers CPU limits vs. longer-running workloads. Single-tenant sandboxes vs. multi-tenant pools. You decide, you migrate, you ship.
Design the system that handles concurrent agent sessions across integrations, an agent responding to an iMessage, checking Calendar, drafting a Slack reply, and updating Linear, all within one session with consistent state.
Define reliability and observability standards for a ~15-person team: SLOs, error budgets, tracing strategy, incident response patterns that actually work at our scale.
Review every significant PR. Set technical direction without blocking velocity.
Ship code daily.