Senior AI Code Evaluator (Python/TypeScript)

Turing; United States; Remote; USD 83,000 - 152,000; Part time

Job summary

Turing is seeking experienced software engineers to evaluate and improve AI coding models. You’ll review AI-generated code and agent behavior across real-world repositories, judge correctness, and identify failure modes to help refine model performance.

In this contractor role, you’ll collaborate with researchers and engineers, design rubrics, and produce clear evaluation data and actionable recommendations to advance coding models.

Qualifications

• 5+ years hands-on software engineering experience
• Proficiency in Python, TypeScript/JavaScript, Go or another major production language
• Experience reviewing AI-generated code and coding agents

Responsibilities

• Evaluate AI-generated code across real-world repositories
• Review agent behavior, tool usage, and code changes for correctness
• Identify technical errors, weak approaches, and recurring model failure modes
• Compare model outputs and explain why one solution is better than another
• Create and refine rubrics and evaluation criteria for coding tasks
• Produce high-quality evaluation data and recommendations for the team
• Build and maintain pipelines and infrastructure for data generation, collection, and evaluation
• Synthesize findings into clear write-ups and updates for the team
• Collaborate with researchers and engineers to translate qualitative judgment into scalable processes
• Share clear, actionable findings with AI researchers and engineers

Skills

5+ years hands-on software engineering

Python

TypeScript/JavaScript

Go

Code review

Written communication

AI coding tools

LLM evaluation

Tools

Git

CI/CD

LLM tooling

Job description

Turing is seeking experienced software engineers to evaluate and improve AI coding models. You’ll review AI-generated code and agent behavior across real-world repositories, judge correctness, and identify failure modes to help refine model performance.

In this contractor role, you’ll collaborate with researchers and engineers, design rubrics, and produce clear evaluation data and actionable recommendations to advance coding models.