Software Engineers: Paid Code Review for AI Agent Evaluation
Terac · Remote · United States ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Paid code review study
- $65 per hour
- Fully remote
- AI evaluation focus
Terac is conducting a paid study to improve how autonomous AI agents are tested against realistic software engineering scenarios. Participants evaluate coding environments and test suites to ensure they accurately reflect complex development tasks.
What you'll do
- Review programming tasks for accuracy and difficulty level
- Verify logic and test cases in evaluation harnesses
- Assess if environments measure software engineering skills
- Explain thought process during code analysis sessions
What you'll need
- Active professional experience as a software engineer
- Experience building or maintaining test suites
- Comfortable reviewing code and speaking aloud
- Familiarity with complex software architecture
How you'll work
- Remote session via screen-sharing
- Guided conversation format
- $65 per hour compensation