AI Code Evaluator - Fully Remote | Upto $90/hr

mercor; United States; Remote; USD 96,000 - 124,000; Full time

Job summary

Mercor is seeking an AI Developer Trace Task Auditor to work remotely, evaluating AI-assisted traces and the quality of AI-generated code to improve model training and evaluation.

You will review end-to-end coding trajectories, provide rubric-based feedback, and collaborate with AI researchers to ensure training data relevance while meeting deadlines in a remote, asynchronous environment.

Qualifications

• 3+ years of professional software development experience.
• Hands-on with AI-assisted coding tools such as Cursor, GitHub Copilot, or Claude Code.
• Strong code-reading and debugging skills for full-stack or backend systems.
• Ability to evaluate multi-step coding trajectories for correctness and best practices.

Responsibilities

• Evaluate the quality and correctness of AI-assisted software-development traces to enhance model training and evaluation.
• Assess end-to-end coding sessions produced with AI-assisted developer tools for correctness, workflow soundness, and reasoning.
• Provide clear, rubric-based written feedback to improve AI model outputs .
• Review complex coding trajectories for alignment with best practices and correctness.
• Collaborate with AI research teams to ensure consistency and relevance in training data.
• Work independently and asynchronously to meet deadlines while enhancing AI model performance .

Skills

Software dev

AI-assisted coding

Code reading

Debugging

Trajectory evaluation

Tools

Cursor

GitHub Copilot

Claude Code

Amazon CodeCatalyst

Job description

About the job Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey . Position: AI Developer Trace Task Auditor Type: Contract Compensation: $70–$90/hour Location: Remote

Role Responsibilities

• Evaluate the quality and correctness of AI-assisted software-development traces to enhance model training and evaluation.
• Assess end-to-end coding sessions produced with AI-assisted developer tools for correctness, workflow soundness, and reasoning.
• Provide clear, rubric-based written feedback to improve AI model outputs .
• Review complex coding trajectories for alignment with best practices and correctness.
• Collaborate with AI research teams to ensure consistency and relevance in training data.
• Work independently and asynchronously to meet deadlines while enhancing AI model performance .

Qualifications Must-Have

• 3+ years professional software development.
• Hands-on experience with AI-assisted coding tools and agentic/spec-driven workflows ( Cursor , GitHub Copilot , Claude Code , or similar).
• Strong code-reading and debugging skills across full-stack or backend systems.
• Ability to evaluate multi-step coding trajectories for correctness and best practice.

Preferred

• Experience with Kiro or Amazon CodeCatalyst .
• Prior work evaluating or grading AI-generated code .
• Contributions to developer tooling .