We are looking for Agent Engineer candidates for a project delivered through Mercor.
What you'll do
- Build and operate LLM agents in production.
- Gain visibility into how agents are actually used inside a company.
- Ship an agent that real users depended on and be on the hook when it broke.
- Figure out how to tell whether an agent got better or worse after a change.
- Run agents that outlive a single request, such as scheduled jobs, long-running work, or cloud sandboxes.
- Observe an organization build an internal assistant and see who adopted it and who did not.
- Work with internal monoagents wired into company data.
- Work with shared company memory.
- Work with reusable skills and playbooks.
- Work with the tool and MCP surfaces agents call.
- Enable others to see what agents did and what they cost.
What you need
- Participate in a short conversational AI interview.
- Think about agent reliability, evaluation, and adoption.
- Discuss tradeoffs made in real systems.
- Share specific experiences.
Nice to have
- Have experience with internal monoagents wired into company data.
- Have experience with shared company memory.
- Have experience with reusable skills and playbooks.
- Have experience with the tool and MCP surfaces agents call.
- Have experience with how anyone sees what agents did and what they cost.
Who you work with
Project and contracting process: Mercor. Applications continue on the provider's website.