Senior AI Coding QA Evaluator (Remote Contract)

G2i Inc.; United States; Remote; USD 138,000 - 276,000; Part time

Job summary

eBSI Export Academy is seeking a highly experienced software engineer to evaluate AI-assisted coding interactions. The role focuses on judging the usefulness, correctness at a high level, and the quality of explanations and reasoning, without writing production code. Strong English communication and direct, opinionated feedback are essential.

You will assess interactions with tools like OpenAI Codex, Claude Code or Cursor and help define what great looks like in AI-assisted development workflows.

Qualifications

• Senior, Staff or Principal-level engineer or equivalent experience
• Strong background in TypeScript/JavaScript or Python
• Hands-on experience with at least one of OpenAI Codex, Claude Code or Cursor
• Deep familiarity with modern AI-assisted dev workflows
• Able to evaluate code without executing it or reviewing every line
• Strong written and spoken English (B2 or above) with detailed feedback
• Comfortable giving direct, opinionated feedback
• High bar for what good engineering looks like

Responsibilities

• Evaluate AI-generated coding interactions end to end
• Judge usefulness, correctness at a high level, and alignment with strong engineer thinking
• Assess explanations and reasoning, not just the code
• Distinguish between levels of response quality (2 vs 4)
• Provide clear, opinionated written feedback and short video explanations
• Help define what great looks like when working with Cursor, Codex and Claude Code

Skills

TypeScript/JavaScript

Python

Engineering judgment

English communication (B2+)

Feedback writing

Evaluating AI-assisted workflows

Tools

OpenAI Codex

Claude Code

Cursor

Job description

eBSI Export Academy is seeking a highly experienced software engineer to evaluate AI-assisted coding interactions. The role focuses on judging the usefulness, correctness at a high level, and the quality of explanations and reasoning, without writing production code. Strong English communication and direct, opinionated feedback are essential.

You will assess interactions with tools like OpenAI Codex, Claude Code or Cursor and help define what great looks like in AI-assisted development workflows.