Senior AI Interaction Evaluator - Engineering Taste

G2i Inc.; Turkey; On-site; TRY 3,286,000 - 13,145,000; Full time

Job summary

G2i Inc. is seeking a Senior AI Interaction Evaluator (Codex / Claude Code) contract role. You will assess AI coding agents on realism, usefulness, and engineering judgment without writing production code.

Start ASAP, 10–20 hrs/week, hourly pay between $50 and $200. You’ll judge how the model thinks like a great engineer and help define high-quality interaction standards for tools like Cursor.

Qualifications

• Strong background in Python programming.
• Experience with OpenAI Codex or similar coding assistants.
• Familiarity with Cursor and AI-first IDEs.
• Ability to judge quality of engineering explanations.
• Comfort giving direct, opinionated feedback.

Responsibilities

• Evaluate AI-generated coding interactions end-to-end.
• Judge usefulness, correctness, and engineering judgment at a high level.
• Assess quality of explanations and reasoning.
• Provide clear, opinionated feedback on what worked and what didn’t.
• Define what great looks like when interacting with Cursor.

Skills

Python programming

Engineering judgment

Feedback writing

Tools

OpenAI Codex

Cursor

Job description

G2i Inc. is seeking a Senior AI Interaction Evaluator (Codex / Claude Code) contract role. You will assess AI coding agents on realism, usefulness, and engineering judgment without writing production code.

Start ASAP, 10–20 hrs/week, hourly pay between $50 and $200. You’ll judge how the model thinks like a great engineer and help define high-quality interaction standards for tools like Cursor.