Senior AI Coding Evaluator (Remote, Part-Time)

BlockchainHQ; United States; Remote; USD 138,000 - 276,000; Part time

Job summary

BlockchainHQ is seeking a highly experienced software engineer (SR+) to evaluate AI coding agents such as Codex and Claude Code. You will assess how the model thinks like a great engineer, focusing on sense-making, usefulness of preambles, and engineering judgment rather than writing production code.

You will provide subjective but rigorous feedback, outline what constitutes great AI-assisted development, and help define standards for interactions with Cursor, Codex, and Claude Code.

Qualifications

• Senior, Staff or Principal-level engineer with strong technical but non-production coding evaluation skills.
• Excellent background in TypeScript/JavaScript or Python and modern AI-assisted dev workflows.
• Fluent written and spoken English (B2+), comfortable providing direct, opinionated feedback.

Responsibilities

• Evaluate AI coding interactions end-to-end without executing code.
• Judge usefulness, correctness at a high level, and engineering judgment in explanations.
• Provide clear, written feedback on what works, what is misleading, and how to improve.

Skills

TypeScript/JavaScript

Python

English writing

Tools

OpenAI Codex

Claude Code

Cursor

Job description

BlockchainHQ is seeking a highly experienced software engineer (SR+) to evaluate AI coding agents such as Codex and Claude Code. You will assess how the model thinks like a great engineer, focusing on sense-making, usefulness of preambles, and engineering judgment rather than writing production code.

You will provide subjective but rigorous feedback, outline what constitutes great AI-assisted development, and help define standards for interactions with Cursor, Codex, and Claude Code.