AI Agent Workflow & Tool-Use Reviewer
Job Description
Work at IXO
Apply your experience in AI agent engineering to paid work at IXO. You will develop realistic evaluation examples and review AI responses for technical correctness, clear reasoning and practical usefulness. The work calls for explanations that identify the actual defect or trade-off and show how a better answer would address it.
Responsibilities
• Evaluate loops, plans and reflection patterns in LangGraph, CrewAI, AutoGen or custom implementations.
• Review tool schemas, validation, recovery, memory and retrieval across single-agent and multi-agent workflows.
• Assess run observability through LangSmith, Langfuse or OpenTelemetry and diagnose retry loops, uncontrolled cost and unsafe exposure of tools.
• Record the assumptions, supporting evidence and corrections needed for another specialist to follow your review.
Experience and expertise
• 3• years building production agents or LLM-powered automation systems.
• Practical depth in at least one agent framework and one custom-built agent loop.
• A thorough understanding of tool-calling APIs across major LLM providers.
• Experience with sandboxed code execution and untrusted-input handling.
• Ability to work confidently with Python or TypeScript for agent development.
• Familiarity with browser-control, OS-control, or CRM-integrated agents is an advantage.
Working arrangements and pay
Remote work in these eligible locations: USA, UK, Canada, Germany, Australia. Planning availability: Flexible, 10-25 hours/week. IXO will confirm the actual start and schedule before acceptance. Compensation is $105 • $170/hr USD. The agreed rate, delivery requirements and review criteria are confirmed before work begins.