This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and manage LLM agents in a production environment.

• Evaluate the reliability, performance, and adoption of agents.

• Execute scheduled tasks, manage long-running agent operations, and utilize cloud sandboxes.

• Analyze the usage and integration of agents within organizations.

• Collaborate with internal monoagents that connect to company data, maintain shared company memory, reusable skills, playbooks, and tool/MCP interfaces.

• Enhance transparency regarding agent activities and associated costs.

• Complete a conversational AI screening interview.

• Engage in a live 30-minute team discussion if selected.

⛳️ Requirements

• Proven experience in building and operating LLM agents in a production setting.

• Successfully deployed an agent relied upon by real users and managed production issues.

• Capability to assess whether an agent's performance has improved or declined following changes.

• Experience managing agents beyond single requests, including scheduled tasks, long-term projects, or cloud sandboxes.

• Familiarity with observing the uptake of internal company assistants.

• Knowledge of internal monoagents, company data, shared company memory, reusable skills and playbooks, tool and MCP interfaces, agent observability, and cost monitoring.

• Must complete a brief conversational AI interview.

• No coding or take-home assignment is necessary.

• Must be available for a live 30-minute discussion if selected.