Remote Contractor — AI Agent Evaluation Engineer

YO AI Labs; Houston (TX); Remote; USD 83,000 - 165,000; Part time

Job summary

YO AI Labs is seeking a Senior Software Engineer to support an AI training project by creating reinforcement learning environments that evaluate models on complex software tasks using Model Context Protocol (MCP) tools. You will design reproducible environments, deterministic verification, and reference solutions for tasks such as bug fixing, feature implementation, codebase refactoring, and performance optimization.

This is a remote, contractor role (~15 hours/week).

Qualifications

• Must have strong proficiency in one or more listed programming languages.
• Solid understanding of algorithms and data structures.
• Experience fixing complex software issues.
• Experience with feature implementation and codebase refactoring.
• Ability to optimize performance and tune systems.
• Excellent written and verbal communication and attention to detail.

Responsibilities

• Create reinforcement learning environments for software engineering tasks.
• Design tasks including bug fixing, feature development, and refactoring.
• Build deterministic verification systems and reference solutions.
• Evaluate AI agents' ability to reason through codebases using MCP tools.
• Document solutions and provide clear technical feedback.
• Deliver reproducible, realistic software engineering scenarios.

Skills

Python

Java

Rust

C++

TypeScript

Algorithms

Debugging

Refactoring

Performance tuning

Communication

Detail-oriented

Distributed systems

Code reviews

Remote collaboration

Job description

YO AI Labs is seeking a Senior Software Engineer to support an AI training project by creating reinforcement learning environments that evaluate models on complex software tasks using Model Context Protocol (MCP) tools. You will design reproducible environments, deterministic verification, and reference solutions for tasks such as bug fixing, feature implementation, codebase refactoring, and performance optimization.

This is a remote, contractor role (~15 hours/week).