Senior Software Engineer - AI Training Envs (Remote)

YO AI Labs; New York (NY); Remote; USD 83,000 - 152,000; Part time

Job summary

YO AI Labs is seeking a Senior Software Engineer contractor to design reinforcement learning environments for evaluating AI models on complex software tasks using MCP tools. The role focuses on reproducible environments, deterministic verification, and reference solutions for bug fixing, feature implementation, refactoring, and performance optimization.

The position emphasizes coding across Python, Java, Rust, C++, or TypeScript, with strong data-structures knowledge and a knack for debugging

Qualifications

• Demonstrated experience to design and implement RL environments for software tasks.
• Ability to build deterministic verification and reference solutions.
• Strong foundation in algorithms and data structures.
• Experience debugging complex software issues and improving performance.

Responsibilities

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

Skills

Python

Java

Rust

C++

TypeScript

Algorithms

Bug fixing

Code refactoring

Performance optimization

Communication

Attention to detail

Job description

YO AI Labs is seeking a Senior Software Engineer contractor to design reinforcement learning environments for evaluating AI models on complex software tasks using MCP tools. The role focuses on reproducible environments, deterministic verification, and reference solutions for bug fixing, feature implementation, refactoring, and performance optimization.

The position emphasizes coding across Python, Java, Rust, C++, or TypeScript, with strong data-structures knowledge and a knack for debugging