Mercor is seeking PhDs and PhD candidates in STEM fields to join a high-impact AI research initiative with a leading AI lab This role involves evaluating and improving cutting-edge large language models (LLMs) by contributing deep domain expertise and academic research insight to benchmark model performance in scientific and technical disciplines, Key Responsibilities: Evaluate the accuracy, depth, and relevance of LLM-generated responses in your domain of expertise, Design and review complex domain-specific tasks to rigorously test model capabilities, Provide structured, high-quality feedback on model strengths and weaknesses, Collaborate with AI researchers to identify model limitations and suggest improvements, Contribute to the development of benchmark datasets and evaluation protocols, Youre a strong fit if you have: A PhD (or are currently a PhD candidate) in a STEM field such as chemistry, physics, mathematics, or related disciplines, Deep familiarity with current research and open questions in your domain, The ability to critically evaluate scientific reasoning, technical writing, and data-driven insights, Strong analytical thinking and attention to detail, Excellent written communication skills, Comfort working independently and asynchronously in remote teams, Role Details: Part-time (1540 hours/week), fully flexible hours, 100% remote and asynchronous?work on your own schedule from anywhere, Compensation & Legal: Hourly contractor role via Mercor, Competitive pay based on expertise and domain, ranging from $20 to $60 per hour, Payments processed weekly through Stripe Connect,
