Code-Data Eval Author (SDET) at Mercor

Code-Data Eval Author — SDET | $30–100/hr | Remote (Americas & Europe)

Mercor partners with frontier AI labs to build the evaluations their coding models are trained and measured against. As a Code-Data Eval Author, you'll design the verifiers, correctness rubrics, and adversarial test cases that determine whether an AI agent's code truly works. This is a high-impact remote contract role ideal for experienced SDETs who want to shape the future of AI development.

What You'll Do

• Design verifiers and correctness rubrics for a wide range of coding tasks
• Enumerate edge cases and build adversarial test suites for AI agent and model evaluation
• Grade agent trajectories and continuously improve test and rubric quality through structured review

What We're Looking For

• ~5+ years of experience as an SDET or Software Test Engineer at a real product organization
• Proficiency in writing both code and tests using automation frameworks such as pytest, Playwright, or Cypress
• Hands-on experience with CI/CD pipelines (SDET background preferred over manual-only QA)
• Strong written communication skills; familiarity with AI tools or evaluations is a plus

Engagement & Compensation

• Fully remote contract with flexible 30+ hours per week
• Hourly rate scaled to your local market: US/Canada $75–100/hr; Europe and LatAm rates scaled to region

Hiring Process — You Get Paid to Interview

The process includes a Mercor Technical Screen, a live Code Review Session, and a Domain Expert Interview. You'll receive $200 upon completing all three steps, regardless of the outcome.