Description

You design and build evaluation frameworks for AI-powered coding systems, creating realistic software engineering tasks to test automated agent capabilities.

This role is remote.

Responsibilities

• Design self-contained coding challenges that accurately assess automated coding agent performance.
• Configure complex development environments for technical projects and testing scenarios.
• Build reliable evaluation frameworks to measure the quality of AI-generated code.
• Debug complex software issues and navigate unfamiliar codebases to resolve technical problems.

Required Skills

• 5+ years of experience in software engineering and development.
• Proficiency in Python, Java, JavaScript, and C++.
• Strong problem-solving and debugging skills.
• Experience with AI systems and software testing methodologies.
• Ability to work independently in remote environments.

Preferred Skills

• Experience with automated coding agents and evaluation frameworks.
• Familiarity with configuring development environments for complex technical projects.

Key Skills

Education

Any Graduate