Senior AI Coding Evaluator (Part-Time, Flexible Hours)

G2I Inc.; Braga; On-site; EUR 60,000 - 85,000; Part time

Job summary

G2I Inc. is seeking a Senior/Staff/Principal-level software engineer to evaluate AI-assisted coding interactions during end-to-end assessments in Braga, Portugal. The role focuses on judging usefulness, correctness at a high level, and alignment with engineering best practices.

You will provide clear, opinionated feedback, record short video explanations, and complete a take-home evaluation with a Loom walkthrough. Flexible 10–20 hours per week, with projects lasting two weeks to a few months.

Qualifications

• Senior, Staff, or Principal-level software engineer, or equivalent experience.
• Hands-on experience with at least one of OpenAI Codex, Claude Code, or Cursor.
• Deep familiarity with modern AI-assisted development workflows.
• Ability to evaluate code without executing it or reviewing every line.
• Strong written and spoken English at B2 level or above.
• Comfort giving direct, opinionated feedback and applying a high bar for engineering quality.
• Flexible schedule of 10-20 hours per week.
• Ongoing work with projects lasting approximately two weeks to a few months.
• New projects may be offered to successful evaluators.
• Start as soon as the take-home exercise is cleared and a project seat is available.
• No interview; the process consists of one take-home evaluation with a recorded Loom walkthrough.

Responsibilities

• Evaluate AI-generated coding interactions end to end.
• Judge whether outputs are useful, correct at a high level, and aligned with strong engineering practice.
• Assess the quality of explanations, reasoning, and guidance provided by coding agents.
• Distinguish between different levels of response quality and help define what excellent interactions look like.
• Provide clear, opinionated written feedback and record short video explanations.
• Complete a take-home evaluation exercise with a recorded Loom walkthrough.

Skills

Senior/Staff/Principal

AI-assisted workflows

Code evaluation without execution

English proficiency B2+

Tools

OpenAI Codex

Claude Code

Cursor

Job description

G2I Inc. is seeking a Senior/Staff/Principal-level software engineer to evaluate AI-assisted coding interactions during end-to-end assessments in Braga, Portugal. The role focuses on judging usefulness, correctness at a high level, and alignment with engineering best practices.

You will provide clear, opinionated feedback, record short video explanations, and complete a take-home evaluation with a Loom walkthrough. Flexible 10–20 hours per week, with projects lasting two weeks to a few months.