Mercor is seeking a Mathematics PhD to author challenging AI evaluation tasks tailored for advanced models. This part time engagement allows you to showcase your mathematical expertise in scientific computing.

As a part of Mercor's collaboration with leading AI labs, you will work on developing original and executable problem sets in various mathematical domains. Your work will focus on identifying gaps in current models, applying your skills in numerical linear algebra, computational finance, or mechanics. This is a unique opportunity to influence AI benchmarks.

Key Responsibilities:
• Curate materials to create research problems from multiple sources
• Formulate comprehensive scientific prompts based on selected materials
• Define grading standards for the evaluation of tasks




• Compare model performance and calibrate tasks effectively
• Ensure successful evaluation tasks by analyzing model behavior

Requirements:
• PhD in mathematics or closely related discipline
• In-depth knowledge of at least two mathematical domains
• Proficiency in Python for scientific applications
• Experience with Git and Docker workflows
• Strong analytical and evaluative skills

Contribute to revolutionary AI evaluation practices at Mercor with your advanced mathematical knowledge and innovative problem-solving skills.
#J-18808-Ljbffr

📌 Mathematics PhD for AI Task Authoring (Ontario)
🏢 Mercor
📍 Ontario