STEM Expert for AI Model Evaluation - Remote

About the Role

We are seeking a STEM Expert for AI Model Evaluation - Remote to join our innovative team at Mercor. In this role, you will develop and refine high-quality reasoning questions in STEM fields to evaluate AI models, ensuring accuracy and instructional quality. This position allows you to work remotely and asynchronously, contributing approximately 20 hours per week. The minimum commitment for this role is one month, making it a flexible opportunity for those looking to engage in meaningful work in the AI space.

What You'll Do

• Design and optimize STEM-based prompts for AI model evaluation.
• Define and document evaluation standards to ensure consistency and quality.
• Conduct model testing and grading to assess AI performance.
• Support benchmarking and quality assurance processes.
• Collaborate with a team of experts to enhance the evaluation framework.
• Work independently while meeting deadlines and project goals.

Requirements

• Strong writing and critical thinking skills are essential.
• A minimum of 2 years of experience in STEM-related fields is preferred.
• A Bachelor’s degree (BS or BA) in Biology, Physics, or Chemistry.
• Familiarity with undergraduate-level biology, physics, and chemistry topics.
• Ability to work independently and manage time effectively.
• Complete an AI-led interview and a written assessment as part of the selection process.

Nice to Have

• Experience in educational content development.
• Previous work in AI or machine learning evaluation.
• Familiarity with online teaching or tutoring platforms.

What We Offer

• Work on your own schedule, providing flexibility in your work-life balance.
• A structured project environment with clear goals and expectations.
• Opportunity to contribute to cutting-edge AI evaluation projects.
• Collaborative team atmosphere with opportunities for professional growth.
• Competitive compensation based on experience and expertise.