Senior Software Engineer – AI Training Environments (Remote)

YO AI Labs; Calgary; Remote; CAD 69,000 - 124,000; Part time

Job summary

YO AI Labs is seeking a Senior Software Engineer (Contractor) to design reinforcement learning environments that evaluate AI models on software tasks using MCP tools. This remote, part-time role emphasizes reproducible scenarios and deterministic verification.

You will tackle bug fixes, feature implementation, codebase refactoring, and performance optimization, with clear task-based deliverables and thorough technical feedback.

Qualifications

• Proficiency in Python 3, Java, Rust, C++, or TypeScript.
• Strong understanding of algorithms and data structures.
• Experience debugging and fixing complex software issues.
• Experience with feature implementation and codebase refactoring.
• Knowledge of performance optimization and tuning.
• Excellent written and verbal communication.
• Attention to detail and thorough problem-solving.

Responsibilities

• Create reinforcement learning environments for software tasks.
• Design tasks covering bug fixing, feature development, refactoring, and optimization.
• Build deterministic verification systems and reference solutions.
• Evaluate AI agents' ability to reason about code and MCP tools.
• Develop realistic, reproducible software engineering scenarios.
• Document solutions and provide technical feedback.

Skills

Python 3

Java

Rust

C++

TypeScript

Algorithms and data structures

Bug fixing

Feature implementation

Codebase refactoring

Performance optimization

Communication skills

Attention to detail

Job description

YO AI Labs is seeking a Senior Software Engineer (Contractor) to design reinforcement learning environments that evaluate AI models on software tasks using MCP tools. This remote, part-time role emphasizes reproducible scenarios and deterministic verification.

You will tackle bug fixes, feature implementation, codebase refactoring, and performance optimization, with clear task-based deliverables and thorough technical feedback.