Remote | Ph.D. / Postdoctoral / Master's Expert

24-Mag • New York, NY

2d • Remote

About The Position

This remote opportunity is for advanced STEM researchers and graduate-level experts to contribute to large language model evaluation and training. The work includes designing challenging scientific problems, developing rigorous step-by-step solutions, identifying areas where advanced AI systems struggle, and collaborating with research teams on evaluation strategies and benchmarks. Relevant fields include physics, applied physics, mathematics, biology, chemistry, and related disciplines. Physics-focused evaluation may cover topics from early undergraduate through Ph.D. level.

The contractor/freelance engagement involves advanced STEM problem design, solution development, model evaluation, error analysis, and benchmark creation. Work is performed remotely in collaboration with AI researchers and technical contributors. Contract extension may be available depending on performance and project requirements. The opportunity description notes that source materials describe the work as full-time, while the formal engagement type is contractor/freelancer. No medical or paid-leave benefits are included under the stated contractor arrangement.

Work must be completed without using confidential, proprietary, unpublished research, restricted datasets, or other protected information belonging to any employer, laboratory, university, research group, client, or third party. The opportunity is available through 24-MAG LLC, which connects experienced professionals with remote consulting opportunities.

Requirements

• Currently pursuing or holding a Master's, Ph.D., or postdoctoral position in a STEM field.
• Background in physics, applied physics, mathematics, biology, chemistry, or a related discipline.
• Strong analytical and research capabilities.
• Ability to solve complex quantitative and conceptual problems, with a strong foundation in advanced STEM reasoning.
• Ability to break difficult concepts into clear explanations and to work with abstraction and multi-step reasoning.
• Strong logical and structured problem-solving skills.
• Ability to provide detailed annotations and constructive feedback.
• Excellent written English communication.
• Strong remote collaboration skills; self-motivated and able to work independently.
• Reliable desktop or laptop setup with a stable internet connection.
• Ability to explain technical concepts using simple language, visuals, and scientific reasoning where appropriate.
• Complete work without using confidential, proprietary, unpublished research, restricted datasets, or otherwise protected third-party information.

Nice To Haves

• Creative and lateral thinking abilities.

Responsibilities

• Design challenging problems across advanced STEM domains and create tasks that probe limitations in model reasoning.
• Develop problems requiring abstraction and multi-step analysis, incorporate symbolic or quantitative reasoning where appropriate, and maintain difficulty across undergraduate through doctoral-level topics.
• Solve complex STEM problems accurately and efficiently; produce clear, structured, step-by-step solutions that explicitly explain assumptions and intermediate reasoning.
• Evaluate large language model responses to advanced STEM tasks and identify recurring weaknesses in reasoning and problem decomposition.
• Analyze errors involving abstraction, symbolic manipulation, or multi-step logic; distinguish conceptual mistakes from calculation or interpretation errors; and provide structured observations to support model improvement.
• Help define STEM evaluation benchmarks, align problem design with research objectives, contribute tasks at varied technical difficulty levels, refine evaluation criteria, and support consistent assessment.
• Collaborate remotely with AI researchers and technical contributors; explain STEM concepts clearly, provide constructive feedback and detailed annotations, and communicate findings in a structured format.
• Work independently while maintaining reliable project delivery.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level