[Hiring] AI Research & Evaluation Specialist @24-MAG

Role Description

We are sharing a specialised part-time consulting opportunity for detail-oriented professionals and postgraduate students with strong research, reasoning, communication, and information-synthesis skills. This role supports an advanced AI research initiative focused on benchmarking and improving cutting-edge language models. Selected professionals will create high-quality research questions, develop accurate reference answers, review information from multiple sources, and prepare structured evaluation materials used to assess and improve AI systems.

Key Responsibilities

• Research & Information Analysis
  • Conduct structured online research across a variety of STEM and non-STEM topics
  • Gather relevant information from multiple sources and synthesise findings clearly
  • Evaluate source quality, relevance, and consistency
  • Identify gaps, contradictions, and important contextual details within research materials
• Question & Answer Development
  • Create high-quality research questions designed to test advanced AI systems
  • Develop accurate, well-supported reference answers
  • Structure questions and solutions so they can be evaluated consistently
  • Apply strong reasoning and written communication across interdisciplinary subject areas
• AI Evaluation Materials
  • Develop structured materials used to benchmark and assess language-model performance
  • Review AI-generated responses for accuracy, reasoning quality, completeness, and clarity
  • Identify subtle errors, omissions, and unsupported conclusions
  • Provide clear written feedback that supports model improvement
• Quality & Independent Work
  • Follow project instructions and evaluation criteria carefully
  • Maintain strong accuracy across independent research and review tasks
  • Manage assignments within a flexible asynchronous workflow
  • Incorporate feedback and project guidance into subsequent work

Qualifications

• Approximately 2–3 years of relevant professional experience in a STEM, non-STEM, research, analytical, or related field
• Current or recently completed master's-level studies
• Alternatively, a bachelor's degree combined with relevant professional experience
• Strong online research and information-synthesis skills
• Excellent written communication and analytical reasoning
• Ability to gather information from diverse sources and summarise it clearly
• Strong attention to detail and comfort working independently
• Availability to contribute approximately 10–20 hours per week
• Access to a compatible MacBook throughout the project

Requirements

• A MacBook with an Apple Silicon M-series processor is required
• Compatible devices include M-series MacBook Pro and MacBook Air models
• The device must support the project's required macOS environment, including macOS 15 or higher where applicable
• A desktop or non-Apple device cannot substitute for the required MacBook setup

Nice to Have

• An interdisciplinary academic or professional background
• Previous research-assistant, analyst, data, or evaluation experience
• Familiarity with AI tools and large language models
• Experience developing research questions, reference answers, or structured assessment materials
• Background in fact-checking, content review, quality assurance, or data annotation
• Experience working independently on research-intensive projects

Why This Opportunity

• Contribute directly to research used to benchmark advanced AI systems
• Work across a broad range of interdisciplinary topics
• Apply research, reasoning, and writing skills to practical AI evaluation tasks
• Build experience creating high-quality training and evaluation materials
• Participate in flexible part-time work with an immediate-start preference

Contract Details

• Independent contractor role
• Fully remote with flexible scheduling
• Expected commitment of approximately 10–20 hours per week
• Immediate availability is preferred
• Competitive rates between $45–$55 per hour depending on experience and project scope
• MacBook with a compatible Apple Silicon M-series chip is required
• The application process includes resume review and a brief approximately 15-minute AI interview focused on research and reasoning skills
• Selected applicants will complete a brief paid assessment
• Weekly payments via Stripe or Wise
• Projects may be extended, shortened, or adjusted depending on project requirements and performance
• Work will not involve access to confidential or proprietary information from any employer, client, or institution