1 month ago
Argentina (city not specified)Mid Level
Responsibilities
- Review realistic programming tasks designed for AI evaluation.
- Assess the accuracy and structure of evaluation harnesses.
- Walk through the reasoning used to check code validity.
- Provide actionable feedback to improve task complexity and realism.
- Share your screen while reviewing the coding environments and discussing potential flaws or improvements.
Requirements
- Professional experience as a software engineer or developer.
- Located in Brazil or Argentina.
- Experience building, reviewing, or testing evaluation harnesses, coding tasks, or test environments.
- Comfort discussing technical architectures and evaluation frameworks.
Benefits
- Paid study participation at $40 per hour.
- Remote participation via a screen-sharing session; the posting does not specify a fixed schedule or duration.
Categories
About Terac
Terac builds an AI-driven research platform and API that connects companies to vetted human experts for participant sourcing, interviews, evaluation, and payouts. Product teams, researchers, and AI labs use it to recruit and compensate niche experts across industries and languages, with Terac handling verification and screening. Privately held and founded in 2025, the company is headquartered in San Francisco and operates as an expert-network marketplace for frontier research.