← नौकरियों पर वापस जाएँ
Code Evaluation
$100 - $200 प्रति घंटा

Senior Software Engineer, AI Training - UK

अभी आवेदन करें → →

विवरण

Evaluate

AI engineering judgment Review complete interactions with AI coding agents and assess whether they reflect the judgment of a strong engineer. This role focuses on evaluation rather than writing production code. Consider whether the response makes sense, whether its opening explanation and reasoning help the user, and whether the exchange would build trust with an experienced developer.

What you will do

  • Evaluate coding interactions from beginning to end for usefulness, high level correctness and engineering judgment.
  • Review explanations and reasoning as well as the code itself.
  • Distinguish between levels of response quality and explain why one response merits a different rating from another.
  • Write direct, specific feedback on what worked, what was misleading and what felt wrong.
  • Help define strong interactions with tools such as Cursor, OpenAI Codex and Claude Code. The work calls for rigorous judgment about qualities that are partly subjective. A technically correct answer still needs to be useful, guide the user well and communicate in a way an experienced engineer would trust.

Required experience

  • Senior, Staff or Principal engineering experience, or equivalent depth of experience.
  • A strong TypeScript/JavaScript or Python background.
  • Practical experience with at least one of OpenAI Codex, Claude Code or Cursor.
  • Deep familiarity with modern development workflows that involve AI assistance.
  • Ability to evaluate code without running it or examining every line.
  • Written and spoken English at B2 level or above for detailed feedback and short recorded explanations.
  • Comfort giving direct, opinionated feedback and holding a high standard for engineering quality. Prior prompt design or evaluation work is helpful. Experience mentoring senior engineers or defining engineering standards is also useful.

Contract and selection

Work remotely from anywhere in the world for 10 to 20 flexible hours per week. Pay is $100 to $200 per hour, depending on experience and location. The engagement is ongoing, with individual projects lasting about two weeks to a few months. Evaluators who perform well may receive further projects. Selection consists of a take-home evaluation exercise with a recorded Loom walkthrough; there is no interview. Work can start after successful completion of that exercise when a project has an available place.

Details

नियुक्ति करने वाली कंपनी

G2i

Category

Code Evaluation

Location

United Kingdom

Languages Required

🇺🇸 English

Posted

Senior Software Engineer, AI Training - UK
$100 - $200 प्रति घंटा
अभी आवेदन करें → →