8 дней назад
Senior Software Engineer (AI Coding Agent Evaluation)
100 - 200$
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Software Engineer (AI Coding Agent Evaluation): Evaluating end-to-end interactions produced by modern AI coding agents such as OpenAI Codex, Claude Code, and Cursor with an accent on engineering judgment, explanation quality, and practical usefulness. Focus on distinguishing response quality, identifying misleading or unhelpful guidance, and defining what excellent AI-assisted development looks like.
Location: Remote, worldwide
Salary: $100–$200/hour depending on experience and location
Company
provides engineering evaluation projects focused on assessing modern AI coding agents and developer workflows.
What you will do
- Evaluate AI-generated coding interactions from start to finish.
- Assess whether responses are useful, correct at a high level, and aligned with strong engineering judgment.
- Review the quality of explanations, reasoning, preambles, and user guidance—not only code syntax.
- Distinguish different levels of response quality and identify what makes an interaction effective or misleading.
- Provide clear, opinionated written feedback and record short video explanations.
- Help define quality standards for tools such as Cursor, OpenAI Codex, and Claude Code.
Requirements
- Senior, Staff, Principal-level engineering experience or equivalent.
- 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 development workflows and the ability to evaluate code without executing it or reviewing every line.
- Strong written and spoken English at B2 level or above is required.
- Ability to make rigorous subjective judgments, give direct feedback, and explain engineering quality clearly.
Nice to have
- Prior exposure to prompt design or evaluation workflows.
- Experience mentoring senior engineers or defining engineering standards.
Culture & Benefits
- Contract engagement conducted remotely worldwide.
- Flexible workload of 10–20 hours per week.
- Ongoing projects typically lasting from approximately two weeks to several months.
- Additional projects may be offered based on successful evaluation performance.
- Work focuses on engineering taste, practical judgment, and clear written feedback rather than production code development.
Hiring process
- Complete one take-home evaluation exercise.
- Submit a recorded Loom walkthrough.
- Start as soon as the evaluation is cleared and a project has an open seat; no interview is required.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →