Senior Python AI Evaluation Engineer (Remote)

Jobgether; España; A distancia; EUR 123.000 - 247.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Competitive hourly pay

Fully remote

Flexible hours

Take-home projects

Descripción de la vacante

Jobgether is partnering with a client seeking a Python Senior Software Engineer, AI Training, based in Spain. The role focuses on evaluating AI-generated coding interactions, judging quality, explanations, and usefulness for advanced AI coding agents.

It is a fully remote, project-based engagement with flexible hours and no traditional interview process. The ideal candidate combines deep Python expertise with critical thinking and clear communication, able to deliver detailed feedback and help

Formación

• Senior, Staff, or Principal-level software engineering experience, or equivalent expertise.
• Strong Python expertise with experience in AI-assisted development workflows.
• Excellent written and spoken English proficiency (B2 level or above).
• Hands-on experience with at least one AI coding tool: Codex, Claude Code, or Cursor.

Responsabilidades

• Evaluate AI-generated coding interactions from start to finish, assessing quality and effectiveness.
• Determine usefulness, technical soundness, and alignment with experienced software engineering practices.
• Assess quality of explanations, reasoning, and recommendations, not just code correctness.
• Apply consistent evaluation standards across varying response quality levels.
• Provide clear, detailed, opinionated feedback on what works or may be misleading.
• Help define quality benchmarks for AI coding agents and related tools.
• Record short video explanations to communicate evaluation findings.

Conocimientos

Python

TypeScript/JavaScript

English proficiency

Herramientas

OpenAI Codex

Claude Code

Cursor

Descripción del empleo

Jobgether is partnering with a client seeking a Python Senior Software Engineer, AI Training, based in Spain. The role focuses on evaluating AI-generated coding interactions, judging quality, explanations, and usefulness for advanced AI coding agents.

It is a fully remote, project-based engagement with flexible hours and no traditional interview process. The ideal candidate combines deep Python expertise with critical thinking and clear communication, able to deliver detailed feedback and help