Senior AI Trainer (Video & LLM Evaluation) — micro1

What the work involves

What you'll do

• Evaluate the performance of AI chat and search tools under standardized, repeatable conditions
• Apply detailed grading guidelines to accurately evaluate, rank, and annotate model responses with structured feedback
• Write, refine, and stress-test prompts that probe model capabilities, covering diverse scenarios, edge cases, and user intents
• Verify consistency and accuracy across evaluations, correcting discrepancies between ratings and the underlying rubric or guidelines
• Utilize AI training tools and platforms to record findings and submit evaluation datasets in alignment with project standards and milestones
• Collaborate with project trainers and contributors to resolve ambiguities, refine guidelines, and ensure evaluation consistency across the team
• Participate in ongoing quality reviews, incorporating feedback to maintain rigorous training and annotation standards

Requirements & eligibility

• Exceptional attention to detail and accuracy in reviewing and evaluating AI-generated content
• Strong written and verbal communication skills for effective collaboration, reporting, and timely updates
• Demonstrated time management and self-organization abilities for independent, remote project participation
• Analytical and problem-solving mindset with a proactive approach to resolving evaluation challenges
• Proven experience with AI model training, RLHF, data labeling, or similar data-centric evaluation projects
• Familiarity with AI products and tools, including prompt engineering and understanding of model behaviors and limitations
• Experience writing evaluation rubrics, grading model outputs, or reviewing AI responses for accuracy, helpfulness, and safety
• Background in AI training, machine learning data preparation, or LLM-focused projects (strongly preferred)
• Physically based in Northern America or Europe