Staff Engineer

⚠️ Please read first

This is a full-time, in-person role based in San Francisco (Presidio) - we work from the office 5 days a week .

You must be based in the Bay Area or willing to relocate before starting .

We require US work authorisation , but are open to O-1 or J-1 visa sponsorship for exceptional candidates.

About Sauna by Wordware

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

Sauna is 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 Calendly 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.

Wordware is the team behind it, 15 people backed by Spark Capital, Felicis, and Y Combinator with a $30M seed, the largest in YC's history. We build from an office in the Presidio, fifty metres from Crissy Field beach, and we work absurdly hard because we can see and feel the outcome every day.

About the Role:

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.

What You'll Do:

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 ~20-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.

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

Who You Are:

Minimum:

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.

Bonus (but not required):

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.

Compensation & Benefits:

Base salary: $280K–$400K + significant equity + health, dental, 401(k), considerable PTO, gym budget, lunch.

The Process:

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

1. Application: Submit your resume and answer a few short questions.

2. 15-minute intro call: Quick check to align on location, motivation, and logistics. If it's a go, we move fast from here.

3. 45-minute technical interview: A deep conversation about systems you've built and decisions you've made. We're looking for depth, judgment, and architectural instinct.

4. System design interview: We'll walk through a real Wordware architecture problem together. We want to see how you think about tradeoffs at scale.

5. Final conversation: We answer your questions and scope out the work trial.

6. Work trial: Paid trial to work on a real project in person with us, usually a few days to two weeks (flexible to do what works for you). See how we work and whether this feels like the right fit on both sides.