AI Code Evaluation Engineer (Python/TypeScript)

Turing Enterprises, Inc.; California; Hybrid; USD 96,000 - 165,000; Full time

Job summary

Turing Enterprises, Inc. is seeking experienced software engineers to evaluate and improve AI coding models. You will review AI-generated code and agent behavior, assess correctness, and determine failure modes to help improve model performance.

You will work across real-world repositories, review coding solutions, and produce evaluation signals and feedback used to improve coding models. This is an independent contractor role with a ~3-month duration and flexible location in North America,

Qualifications

• 5+ years of hands-on software engineering experience.
• Proficiency in Python, TypeScript/JavaScript, Go or other major production language.
• Strong code-review skills and technical judgment.

Responsibilities

• Evaluate AI-generated code and solutions across real-world repositories.
• Review agent behavior, tool usage, and code changes for correctness and quality.
• 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 to improve coding models.
• Build and maintain pipelines and infra for data generation and evaluation workflows.
• Synthesize findings into clear write-ups and recommendations 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

Python

TypeScript/JavaScript

Go

Code-review

Written communication

LLM tools experience

Job description

Turing Enterprises, Inc. is seeking experienced software engineers to evaluate and improve AI coding models. You will review AI-generated code and agent behavior, assess correctness, and determine failure modes to help improve model performance.

You will work across real-world repositories, review coding solutions, and produce evaluation signals and feedback used to improve coding models. This is an independent contractor role with a ~3-month duration and flexible location in North America,