Role OverviewYou'll design coding tasks that challenge frontier AI coding agents. Each task is a self-contained Docker environment with a broken piece of software; an AI agent attempts the fix; automated tests verify the outcome.
What You Will Do
Invent a realistic developer scenario, build a reproducible Docker environment, write a pytest, create an instruction.md, and write a reference solve.sh. Calibrate difficulty so current state-of-the-art agents solve the task 20–60% of the time.
Why It Might Be a Fit
You have 3+ years of production software development in one backend stack, Python + pytest fluency, Docker authoring, and AI coding agent experience. You're a good fit if you have domain depth in Security, System Administration, Scientific Computing, DevOps, or Git internals.
Requirements
- 3+ years of production software development in one backend stack — Python, Go, Node.js, Java, or Rust
- Python + pytest fluency
- Docker authoring
- AI coding agent experience — Claude Code, Cursor, Roo Code, or similar, on non-trivial work
- English — B2+ written
Benefits
- Paid contributions, rates up to $35/hour
- Task-based compensation equivalent to hourly rate, depending on performance and volume
- Some projects include incentive payments
]]>