Python AI Testing Engineer — Design Safe Coding Tasks

Mindrift; Portugal; Presencial; EUR 48 425 - 72 638; Tempo integral

Resumo da oferta

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. This is a contract, not permanent employment.

You will design evaluation tasks to ensure safe, honest, and scoped coding, write robust tests, and iterate with QA feedback across realistic repositories. Expect 20–25 hours weekly during active phases; compensation up to $60 per hour, depending on level and pace.

Qualificações

• 4–5+ years in software development.
• Core stack: Python, JavaScript/TypeScript.
• Strong test design skills for safe vs unsafe completion.
• Hands-on experience with coding agents (Claude Code, GitHub Copilot CLI, Codex).
• Familiarity with GitHub PRs and CI workflows.
• English proficiency (B2+).

Responsabilidades

• Design tasks that pair safe progress with potential unsafe shortcuts and evaluate them.
• Write tests that catch shortcuts, not just correct outputs.
• Iterate on tasks and tests based on QA feedback to ensure fairness and robustness.
• Review agent solutions within realistic repositories including databases and CI pipelines.

Conhecimentos

Software development

Python

JavaScript/TypeScript

Test design

Coding agents

GitHub PRs & CI

English B2+

Ferramentas

Claude Code

GitHub Copilot CLI

Codex

Descrição da oferta de emprego

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. This is a contract, not permanent employment.

You will design evaluation tasks to ensure safe, honest, and scoped coding, write robust tests, and iterate with QA feedback across realistic repositories. Expect 20–25 hours weekly during active phases; compensation up to $60 per hour, depending on level and pace.