STEM Generalist Evaluator at Mercor

STEM Generalist Evaluator | $35–60/hr | Remote

Join Mercor’s high-impact AI research initiative as a STEM Generalist Evaluator. This part-time contractor role is ideal for PhD holders, doctoral candidates, or exceptional Master’s graduates in biology, physics, chemistry, engineering, computer science, mathematics, or related disciplines.

• Apply deep subject-matter expertise to rigorously evaluate and enhance large language models (LLMs) in partnership with a leading AI lab.
• Review and assess the accuracy, scientific depth, and domain relevance of LLM-generated answers across advanced topics including molecular biology, genetics, classical mechanics, quantum physics, physical chemistry, computer science, engineering, and humanities.
• Identify factual inaccuracies, logical flaws, and reasoning gaps in AI outputs.
• Work independently and asynchronously using provided evaluation tools.

Requirements:

• PhD or PhD candidate in a STEM field (or exceptional Master’s graduate).
• Strong familiarity with graduate-level science and research problem solving.
• Excellent written communication and attention to detail.
• Comfortable working independently and remotely.
• Basic Python knowledge preferred.

Role Details:

• Part-time (approx. 20 hours/week).
• Remote and asynchronous work.
• Contractor position via Mercor, weekly payments via Stripe Connect.

Mercor connects top professionals with leading AI initiatives and is backed by renowned investors. Make an impact in AI research while leveraging your STEM expertise.