Role OverviewDesign 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, and calibrate difficulty so current state-of-the-art agents solve the task 20–60% of the time.
Why It Might Be a Fit
You'll have the opportunity to work on project-based AI opportunities, design challenging tasks, and contribute to agent-evaluation benchmarks. You'll also have the chance to review other authors' tasks as a QA reviewer.
Requirements
- 3+ years of production software development in one backend stack — Python, Go, Node.js, Java, or Rust.
- Python + pytest fluency — required regardless of primary stack.
- Docker authoring — reproducible Dockerfiles, pinned dependencies, multi-stage builds when needed, non-root user.
- Linux & Bash — comfort debugging inside containers (strace, lsof, journalctl); shell beyond set -euo pipefail.
- AI coding agent experience — Claude Code, Cursor, Roo Code, or similar, on non-trivial work.
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.
]]>