Junior Web Developer – Remote AI Agent Evaluation

About the role

We are looking for a Junior Web Developer to help design, evaluate and improve autonomous AI agents across multiple large-language models. The work is fully remote and focuses on building and testing production-grade software that interacts with live tools in domains such as health, education and daily life.

Key responsibilities

• Write clear evaluation rubrics and objective pass/fail criteria for AI agents.
• Debug agent execution traces to spot failure patterns.
• Stress-test agents against edge cases, prompt injection and tool misuse.
• Assess modular software architecture and multi-turn system interactions.
• Provide high-density technical feedback to support LLM training.

Required profile

• Experience in backend engineering, AI automation or complex systems integration.
• Proven ability to build and maintain production-grade, modular software services.
• Strong command of at least two major programming languages.
• Hands-on experience with live, non-mocked environments and multi-turn interactions.

Required skills

• Python
• JavaScript
• Go
• Java
• SQL databases
• Supabase API integration
• Gmail API integration

What we offer

• Hourly rate of $30-$50 depending on experience and task complexity.
• Weekly payments via PayPal or AirTM.
• Fully remote work with flexible task assignments.