Applied AI 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

Most AI products hand you a coworker on day one and hope you trust it. Sauna is the coworker you raise: it starts by learning how you work, earns autonomy task by task, and ends up running hours of work on its own while you keep taste, review, and the final say. Wordware is the ~20-person team behind it, backed by Spark Capital, Felicis, and Y Combinator with a $30M seed, the largest in YC history. We build from a San Francisco office in the shadow of the Golden Gate Bridge, and we work absurdly hard because we can see and feel the outcome every day.

About the Role:

As an Applied AI Engineer, you’ll be responsible for building, refining, and scaling the agent systems inside Sauna, from architecture to evals to deployment.

We care about what works in production: fast response times, predictable behavior, traceability, and uptime.

You’ll work across infra, frontend, and product to make sure the agents people build inside Wordware actually work.

A few examples of what you might work on:

• Implement multi-step, tool-using agents that hit real APIs and handle retries, auth, timeouts, and edge cases.

• Design agent memory systems that persist relevant state across runs, e.g. memory migrations, context organization, and orchestration state.

• Create agents that proactively do work and send you reminders.

• Own and evolve our eval framework: both automated checks and human-in-the-loop scoring.

• Plus whatever else you see fit.

Who You Are

Minimum

• 3+ years of engineering experience, including time shipping production software.

• You've built and deployed agent-like systems: multi-step LLM pipelines, tool-using bots, scripted assistants, or similar.

• Hands-on experience with:

  • Agent orchestration and memory management (e.g. memory migrations, state organization).

  • Tool use and orchestration (e.g. calling real APIs, using plugins, auth flows)

  • Evaluation: success metrics, regression testing, and improving agent behavior over time

• You write production-grade code and can work across systems without needing a spec.

• You'd rather ship than polish forever.

Bonus (not required)

• Shipped agents that live in the wild, used by customers, not just internal demos.

• Familiarity with LLM ops, tracing, observability, and failure handling.

• You've been a founder or early engineer, and it shows in the bar you hold your own work to.

Compensation & Benefits:

Base salary: $180K–$240K + meaningful early-stage 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 quick questions.

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

3. System design interview (1 hour): We dig into how you think about agent design: architecture, tradeoffs, and your experience building AI harnesses and agent systems.

4. Technical interview (optional follow-up): A coding round testing hands-on engineering fluency and speed, only if we need a closer look.

5. Final conversation: Answer any questions and scope out the work trial.

6. Work trial: Paid, in-person. Typically 5 days, though we're flexible on timing depending on the role. You’ll work on something meaningful with us.