Evaluate advanced AI agents remotely with Outlier, applying technical feedback, debugging, and complex systems integration expertise.

This freelance opportunity supports projects training large language models to function as proactive, multi-step agents. Contributors help improve autonomous systems by analyzing complex behaviors and real-world architectural workflows. The work includes writing evaluation rubrics, debugging agent traces, and stress testing agent performance.

Key Responsibilities:

- Analyze complex autonomous agent system behaviors
- Write detailed evaluation rubrics for agents
- Debug multi-turn agent traces and interactions
- Stress test agents using live environments
- Identify subtle failures in agent behavior

Requirements:

- Two or more years of relevant experience
- Robust attention to technical detail
- Experience building production-grade modular software
- Experience with live tools and real interactions
- Clear, high-density technical feedback skills

Use agent debugging, evaluation, and systems expertise to help Outlier improve proactive AI systems.

📌 AI Agent Evaluation Engineer (Kitchener)
🏢 Outlier
📍 Kitchener