Key skills
DockerJavaScriptOpen SourcePythonTypeScriptAIMLLLMCI/CD
About this role
Role Overview
- Create high quality engineering artifacts used to train and evaluate advanced AI coding assistants
- Design realistic coding tasks
- Review model-generated code
- Write high quality examples
- Evaluate coding agent behavior
- Collaborate with leading AI labs and teams developing next generation coding agents
Requirements
- 4+ years of professional software engineering experience
- Deep experience with CI/CD, automated testing, and code review best practices
- Proficient in Python and JavaScript/TypeScript
- Extensive hands-on use of AI coding tools such as Claude Code, Codex CLI, or Cursor
- Working knowledge of LLM evaluation, benchmarking, and structured model assessments
- Strong Docker and DevOps skills or applied ML engineering experience (preferred)
- Active contributions to open source projects (preferred)
- Experience writing technical documentation, tutorials, or challenge problems (preferred)
Tech Stack
- Docker
- JavaScript
- Open Source
- Python
- TypeScript
Benefits
- Flexible hours with a minimum commitment of 20+ hours per week
- Project length 1 to 2 months, with potential to extend
- Independent contractor role