AI Engineer, Agent Infrastructure
Zed, San Francisco Office
The role
We're hiring an engineer to own the infrastructure layer behind our production AI agents.
This is not a prompt engineering role. It's not a UI role. It's about the harness around LLMs — the systems that determine how agents actually execute tasks, interact with tools, access internal and external systems, stay within permission boundaries, and behave reliably in production.
You'll sit at the intersection of backend infrastructure and product, and what you build will define how AI is deployed across the company.
What you will do
- Build and own the execution layer for AI agents — task orchestration, tool calling, state management
- Define how agents interact with internal systems and external APIs
- Design sandboxed environments and permissioning models for safe, controlled agent execution
- Build evaluation, monitoring, and debugging infrastructure for agent behavior in production