You understand Rox’s architecture, agent runtime, and infrastructure stack deeply enough to contribute to production systems.
You are independently designing and improving core systems tied to agent reliability, execution, and retrieval performance.
You help define the technical foundation that enables autonomous enterprise workflows to operate reliably at massive scale.
Enterprise AI systems are moving toward autonomous execution.
The hard problem is not generating outputs — it’s building reliable systems that can reason, retrieve context, coordinate actions, and operate deterministically under real-world enterprise constraints.
We believe this requires a new category of infrastructure engineering.
That is the problem space this team exists to solve.
This role is based onsite in San Francisco.
We strongly believe that the speed and complexity of the problems we are solving benefit from in-person collaboration. We actively relocate exceptional engineers from around the world and currently have team members who have moved from Europe, Canada, Asia, and Australia to join Rox.
If you want to work on deep infrastructure problems at the frontier of autonomous systems, we’d love to talk.