£140.00 hourly
Mercor
Remote
Mercor is partnering with a leading AI research lab on Project Vesuvius , an initiative designed to evaluate and enhance the ability of large language models (LLMs) to generate structured, high-quality research plans for open-ended machine learning problems.
We are seeking Machine Learning Researchers and PhDs to serve as annotators who will assess and provide structured feedback on AI-generated research plans. The goal is to improve how LLMs function as brainstorming partners for machine learning research.
This is a remote, short-term engagement with flexible hours and opportunities to contribute to frontier AI evaluation and research.
Key Responsibilities
Evaluate and compare AI-generated research plans for clarity, feasibility, and technical soundness.
Design and compile ML tasks based on real-world challenges and research competitions.
Draft detailed, executable natural language...