Remote | LLM Personal Assistant Evaluation Specialist -- $70-$180/hour
2 days ago
New York
Job Description We are sharing a specialised part-time consulting opportunity for advanced LLM power users experienced in personalized AI workflows, rubric-based evaluation, real-world task assessment, personal productivity systems, and high-context decision support. This role supports current and upcoming remote consulting opportunities focused on evaluating how AI systems handle personalized, real-world life tasks across food, health, productivity, career, learning, research, planning, and personal workflow scenarios. Selected professionals will create realistic prompts, complete complex AI-assisted tasks, record workflow execution, design or apply detailed rubrics, and evaluate whether AI outputs are useful, personalized, practical, safe, and successful in real-life contexts. Key Responsibilities Professionals in this role may contribute to: Personalized AI Task Evaluation • Create written responses, prompts, and explanations for complex personal-life tasks, • Evaluate whether AI outputs are practical, well-reasoned, personalized, realistic, and successful, • Identify where outputs succeed, miss context, overreach, provide generic advice, or fail to account for real constraints, • Use hands-on LLM experience to assess real-world usefulness across high-context personal workflows Rubric Design & Quality Assessment • Apply structured rubrics and quality criteria to evaluate AI system performance, • Create detailed evaluation rubrics for complex personal tasks and multi-step workflows, • Judge outputs against criteria involving usefulness, personalization, reasoning quality, safety, completeness, and success conditions, • Write clear, specific, and well-supported feedback explaining evaluation decisions Real-World Workflow Execution • Execute AI-assisted tasks while recording screens according to project instructions, • Review task performance across tools, prompts, reasoning steps, outputs, and final recommendations, • Complete research-intensive personal workflows end-to-end within expected turnaround timelines, • Maintain careful documentation of task setup, execution, rubric design, and evaluation results Ideal Profile Strong candidates may have: • Heavy personal usage of LLM products and AI tools, • Experience using AI for multi-step tasks, planning, research, decision-making, personal workflows, or life administration, • Familiarity with tools such as ChatGPT, Claude, Gemini, Perplexity, Cursor, Windsurf, Codex, or other AI agents, • Strong ability to explain what makes an AI output useful, incomplete, unsafe, unrealistic, generic, or poorly personalized, • Extensive rubric experience, including prior rubric design, evaluation, and quality assessment work, • Strong written judgment, attention to detail, and ability to evaluate against structured criteria, • Ability to complete tasks within 24 hours when project timing requires Educational Background • Formal degree requirements may vary based on project needs, • Practical experience using LLMs for complex personal workflows, rubric-based evaluation, research, writing, QA, product testing, or AI assessment is highly relevant, • Experience in education, research, operations, productivity systems, coaching, writing, product evaluation, user research, or AI workflow design may be especially valuable Nice to Have • 100+ hours of prior rubric-related work involving rubric design, evaluation, model assessment, quality review, or structured judgment, • Experience evaluating AI tools across personal productivity, career planning, food recommendations, learning workflows, health-adjacent reasoning, or personal research tasks, • Strong familiarity with personal AI workflows involving calendars, reminders, errands, job applications, LinkedIn, resumes, study plans, restaurant selection, or decision support, • Ability to record screen-based workflows clearly and follow detailed task instructions, • Access to a desktop or laptop computer suitable for project work and screen recording Why This Opportunity • Apply advanced LLM power-user experience to structured remote project work, • Contribute to high-quality evaluation of personalized AI assistant workflows, • Work on flexible assignments involving practical, real-world personal tasks across multiple domains, • Use your judgment to help assess whether AI systems are truly useful, personalized, realistic, and successful, • Remote structure with competitive hourly compensation Contract Details • Independent contractor role, • Fully remote with flexible scheduling, • Eligible professionals should be based in the United States depending on project needs, • Expected commitment of approximately 15–40 hours per week depending on project availability and scope, • Participants may be asked to complete a paid work trial as part of onboarding, • Work trial compensation may be approximately $30 upon completion depending on project requirements, • Tasks may require 24-hour turnaround depending on assignment timing, • Desktop or laptop computer required for project work and screen recording, • Competitive rates between $70–$180 per hour depending on expertise, project scope, and task type, • Weekly payments via Stripe or Wise, • Projects may be extended, shortened, or adjusted depending on scope and performance, • Work will not involve access to confidential or proprietary information from any employer, client, or institution About the Platform This opportunity is available through 24-MAG LLC. We connect experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams. By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy: https://www.24-mag.com/privacy-policy.