About the role
You'll design and ship the multi-agent systems that run real operational work inside customer stacks — building, deploying, and tuning AI employees end to end. You care about reliability in production, not just demos, and you like working close to real customer problems.
What you'll do
- Architect multi-agent workflows that handle end-to-end operational tasks.
- Integrate agents into customer tools — CRM, ERP, Slack, email, and industry systems.
- Build evals and guardrails so agents are reliable and safe in production.
- Deploy and operate agents on our infrastructure; monitor and continuously improve them.
- Work directly with customers to scope and tune their first AI employee.
What you bring
- Strong software engineering in Python and/or TypeScript.
- Hands-on experience building with LLMs and agent frameworks.
- A bias for shipping and measuring, not just prototyping.
- Comfort owning systems in production.
Nice to have
- RAG, tool-use orchestration, or evals experience.
- Infra / DevOps experience.
- Experience deploying AI into real business workflows.
Sound like you?
Send us a note with your background and anything you've built. We review every application and reply.