Senior Software Engineer, AI Training

This is a fully remote position, open to applicants in New Zealand.

📋 Description

• Assess the quality of interactions with contemporary coding agents like OpenAI Codex and Claude Code.

• Evaluate AI-generated coding interactions from start to finish.

• Determine if outputs are useful, correct at a high level, and in line with strong engineering principles.

• Evaluate the clarity of explanations and reasoning, not solely the code itself.

• Differentiate between various levels of response quality.

• Provide clear, opinionated written feedback on what was effective, what was ineffective, and what appeared misleading.

• Assist in defining what excellence looks like when utilizing Cursor, Codex, and Claude Code.

• Create short video explanations of evaluations.

• Undertake projects that last approximately two weeks to several months, with new assignments available to successful evaluators.

⛳️ Requirements

• Senior, Staff, or Principal-level engineer, or possess equivalent experience.

• Strong proficiency in TypeScript/JavaScript or Python.

• Practical experience with at least one of OpenAI Codex, Claude Code, or Cursor.

• Extensive knowledge of modern AI-assisted development workflows.

• Capability to evaluate code without executing it or reviewing each line.

• Proficient written and spoken English (B2 level or above).

• Comfortable delivering direct, opinionated feedback.

• High standards for engineering excellence.

• Previous exposure to prompt design or evaluation workflows is a plus.

• Experience in mentoring senior engineers or establishing engineering standards is advantageous.

• Must complete a take-home evaluation assignment with a recorded Loom walkthrough.

• Must consent to a simple background check for the project.

🏝️ Benefits

• Flexible working hours: 10–20 hours per week.

• Continuous project opportunities for evaluators who perform well.

• Remote work arrangement available worldwide.