Remote Software Engineer – AI Model Evaluation

About the role

Turing is seeking a remote Software Engineer to evaluate and improve AI-generated code. You will work closely with researchers to create high‑quality datasets, curate code examples, and refine solutions across multiple programming languages.

Key responsibilities

• Curate and correct code examples in Python, JavaScript (ReactJS), C/C++, Java, Rust, and Go.
• Evaluate AI‑generated code for efficiency, scalability, and reliability.
• Collaborate with cross‑functional teams to enhance AI‑driven coding solutions.
• Build verification agents that detect error patterns and assess code quality.
• Hypothesize software engineering workflow steps and test model capabilities.
• Design automated verification mechanisms for software tasks.

Required profile

• Minimum 3 years of professional software engineering experience.
• Strong background in building full‑stack, production‑grade applications.
• Deep understanding of software architecture, design, debugging, and code review.
• Excellent written and oral communication for clear evaluation rationales.
• Based in the US, Canada, or Western Europe with partial PST overlap availability.

Required skills

• Python
• JavaScript (including ReactJS)
• C / C++
• Java
• Rust
• Go

What we offer

• Flexible contractor engagement: 10–40 hrs/week.
• Initial 1‑month contract with potential extensions.
• Remote work from any eligible location.