Member of the Technical Staff — Applied AI, Fullstack
stuut-ai · San Francisco · onsite
USD 185,000 to 250,000 · period not stated
ABOUT STUUT
Stuut is the AI coworker that runs order-to-cash for the world’s leading enterprises. Across order management, credit, collections, payments, cash application, disputes and deductions, Stuut does the work end to end and keeps going until the cash hits the bank.
Over 150 companies, spanning the mid-market to the Fortune 50, including Honeywell, ZoomInfo and PerkinElmer, use Stuut to unlock up to 40% more cash flow and cut DSO by 47%. More than $3 billion has moved through the platform to date.
Founded in New York by Tarek Alaruri and Ben Winter, Stuut has raised $93 million from Insight Partners, Andreessen Horowitz, M12, Microsoft’s Venture Fund, and others. Learn more at stuut.ai http://stuut.ai.
THE ROLE
Agent experience is a plus, not a requirement. If you're an exceptional engineer who wants to do this work, we'll teach you the rest on the job.
The hard part of putting agents into finance workflows isn't getting them to do something. It's knowing when an agent can safely act, and checking that it got it right. That is this role.
You'll build agents that take real receivables work from start to finish, the harness around them, and the product that lets finance teams trust them. You'll work directly with customers to learn how AR teams actually work, and turn that into agents that hold up in production.
WHAT YOU'LL DO
- Build agents that take receivables work from start to finish: applying payments, chasing overdue invoices and resolving deductions.
- Build the agent harness: the tools, structured outputs, guardrails and human approvals that decide when an agent acts, waits or escalates.
- Make every agent action traceable, and every write to a customer's ERP safe to retry and easy to review.
- Build the product, from APIs and data models to the UI, where finance teams set rules, review decisions and steer agents.
- Write evals against real customer outcomes, and turn each failure into a fix in the harness.
- Work with customers to learn how AR teams actually work, and turn their edge cases into better agents.
YOU MIGHT BE A FIT IF YOU…
- Have built an agent that calls tools and takes real actions, at work or on your own.
- Ask "how would we know if this is wrong?" before you ship, and answer it with evals and traces.
- Have handled long-running agent work: state, retries, and runs that pause for a person and resume.
- Want to work where a wrong action costs a customer real money, and design for that.
- Like learning a new domain from the people who do the work. No finance background required.
BIG PLUS
- Harness engineering: designing the tools, context, guardrails and feedback loops around a model.
- Pydantic AI, which our agents run on.
US Compensation
- Top-of-market salary and equity package
- Benefits (for U.S.-based full-time employees)
- Medical, dental & vision insurance coverage for you
- 401(k) & Match
- Equity
- Flexible PTO
- Parental Leave
Stuut is an equal opportunity employer committed to building a team with diverse backgrounds, perspectives, and experiences. We do not discriminate based on race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, genetic information, or any other characteristic protected by applicable law.
We are also committed to providing reasonable accommodations throughout the application and interview process. If you need any accommodations, please do not hesitate to reach out.