Staff Software Engineer, Agent Systems and Product Quality

CharacterQuilt is building an AI workforce for enterprise marketing teams.

Humans decide what should exist and approve it. Our agents create the work, operate the customer's real software, and return proof of what happened. We want one person with judgment to be as powerful as an entire agency.

We have raised $13 million and are building a small, deeply technical team in New York City. Everyone works directly with the founder and CEO, close to customers and production. We work together five days a week in Union Square because the product, customer, and engineering loops are still extremely tight.

Enterprise marketing still runs through agencies because launching one campaign means coordinating specialists across Marketo, HubSpot, Meta, LinkedIn, CMSs, and a dozen other systems. It takes weeks.

CharacterQuilt uses computer-use agents to do that work inside the software companies already use. A campaign that took three months can now ship in two days. We raised $13M and were one of the fastest-growing companies in YC's P26 batch.

You'll own agent quality across CharacterQuilt.

That means the agent architecture, the evaluation system, and the product loop that turns customer feedback into better behavior. The goal is not a better demo. It is agents that reliably create and deploy real work inside real enterprise systems.

• Agent architecture across planning, browser use, tools, context, skills, and verification.
• Evaluations built from real customer failures, not synthetic benchmarks.
• Quality across creative, documents, websites, emails, and campaign deployment.
• The boundary between model judgment and deterministic software.
• The technical bar for a growing agent-systems team.

• You've shipped production agents, applied AI systems, or developer tools.
• You know how to turn failures into useful evaluations and product changes.
• You have unusually high standards for both engineering and the end product.

Five days a week in Union Square. $250K to $350K base plus 0.5% to 3% equity. We do not sponsor US visas.

We build computer-use agents that take enterprise work from intent to production.

The hard part is not teaching a model to click. It is authenticated browser execution, durable state, tenant isolation, skill and context hydration, safe external side effects, exact readback, evaluation, and recovery when models, browsers, or providers fail.

Our stack includes TypeScript and Next.js, Python and FastAPI, Postgres and Supabase, AWS EC2 and S3, browser automation, and frontier models. Engineers work across the product, database, worker, sandbox, browser, integrations, and customer-visible result.

1. A founder conversation about the agent systems you have shaped and the work you want to own next.

2. A focused technical screen on a real agent-quality and verification failure.

3. A systems deep dive covering context, skills, tools, browser state, evaluations, approval, and feedback loops.

4. A paid two-day onsite work trial on a bounded agent-system and evaluation project.

5. Senior references and a direct offer conversation with the founder.

The process is designed to create shared evidence. We will share the purpose and rubric for every stage. The paid work trial gives both sides a concrete view of the work, the code, the pace, and the relationship.