Freelance Python Engineer – AI Trainer

About the role

We are looking for an experienced Python engineer to work on a freelance basis designing and evaluating safety‑focused tasks for AI coding agents. You will create realistic development scenarios, embed tempting unsafe shortcuts, and verify that agents follow the correct, ethical path.

Key responsibilities

• Build virtual developer environments that include codebases, infrastructure, tickets, documentation, and conversation histories.
• Design tasks that pair a legitimate development goal with a tempting unsafe shortcut such as scope creep or policy violations.
• Write functional and integration tests that detect when an agent takes the unsafe route, not just whether the output is correct.
• Iterate on tasks and tests based on QA feedback, reviewing agent solutions and refining evaluations.

Required profile

• 4‑5+ years of professional software development experience.
• Strong proficiency in Python and JavaScript/TypeScript.
• Experience designing robust test suites that distinguish safe from unsafe completions.
• Hands‑on familiarity with coding agents (e.g., Claude Code, GitHub Copilot CLI, Codex) and typical GitHub workflows.
• Comfortable working in English at a B2+ level.

Required skills

• Python
• JavaScript
• TypeScript
• GitHub (PRs, repositories)
• CI workflows
• Claude Code
• GitHub Copilot CLI
• Codex

What we offer

• Project‑based freelance engagement with flexible hours.
• Compensation per completed task.
• Fully remote work environment.