Staff Software Engineer, Agent Infrastructure and Reliability

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 set the architecture and reliability bar for the infrastructure that runs every CharacterQuilt agent.

This is not a narrow platform role. You'll own the system from Postgres and the filesystem through workers, sandboxes, authenticated browsers, and the product state customers see.

• Worker and sandbox orchestration that stays correct through crashes, retries, and timeouts.
• Durable execution, idempotency, recovery, and observability for consequential agent actions.
• Browser profiles, credentials, tenant isolation, and authenticated session reliability.
• The API, CLI, and MCP surfaces around our agent runtime.
• A simpler system and a higher engineering bar as the team grows.

• You've owned production distributed systems, developer infrastructure, or browser automation.
• You can debug across application code, databases, queues, networks, and filesystems.
• You want staff-level scope without staff-level distance from the work.

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 most consequential systems you have owned and what you want from your next company.

2. A focused technical screen on a real partial-failure problem.

3. An architecture deep dive covering agent execution, authenticated browser state, publication, observability, and recovery.

4. A paid two-day onsite work trial on a bounded, production-shaped systems problem.

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

The process is designed to create shared evidence. We will tell you what each stage measures. The work trial is paid, scoped safely, and gives you the same chance to inspect us that we have to inspect your work.