Leverage your PhD expertise as an AI Evaluation Specialist at Mercor. Collaborate with top AI labs to create groundbreaking scientific evaluation tasks that challenge current models.
Mercor seeks scientists with a PhD or Master's to craft AI evaluation benchmarks in scientific computing. You will author original research problems in domains like numerical linear algebra and computational finance. This role combines mathematical depth with practical coding skills, requiring a commitment of 20+ hours per week over six weeks.
Key Responsibilities:
• Source material from papers, datasets, or custom scenarios
• Write scientific prompts based on established inputs
• Develop grading criteria for correct answers
• Calibrate tasks against leading AI models
• Ensure tasks are challenging enough for frontier models
Requirements:
• PhD in mathematics or closely related field
• Depth in two subdomains like computational finance
• Proficiency in Python or R for scientific tasks
• Familiar with Git and Docker workflows
• Bonus: Publications in peer-reviewed journals
Utilize your analytical and coding skills to advance AI research at Mercor.
#J-18808-Ljbffr

📌 AI Evaluation Specialist at Mercor (Toronto)
🏢 Obsidian
📍 Toronto