Rose Limos

Detail-oriented AI Response Evaluator with experience training and evaluating Large Language Models (LLMs) through prompt-based conversations. Skilled in assessing AI-generated responses for accuracy, reasoning, relevance, safety, factual consistency, and instruction-following. Experienced in data annotation, response ranking, quality assurance, and providing structured human feedback to improve AI model performance.

Adept at following detailed project guidelines, maintaining high-quality standards, and working independently in remote environments.

AI Response Evaluator - Outlier AI - Remote

• Conducted prompt-based conversations with AI language models to evaluate performance and response quality.
• Assessed AI-generated content for accuracy, relevance, reasoning, clarity, completeness, and instruction-following.
• Compared multiple model responses and selected the best output according to project guidelines.
• Identified hallucinations, factual errors, logical inconsistencies, bias, and unsafe content.
• Provided structured ratings and written feedback to improve generative AI model performance.
• Consistently followed annotation guidelines and maintained high-quality evaluation standards.
• Worked independently while meeting project quality and productivity expectations.

Production Operator - Tamiya Philippines Inc.

(2005-01 - 2009-12)

• Assembled plastic model kits following detailed manufacturing specifications.
• Applied decals and stickers with precision and consistency.
• Performed quality inspections to ensure products met company standards.
• Maintained productivity and accuracy in a fast-paced production environment.

Production Operator - Cebu Mitsumi Inc.

(2004-01 - 2005-12)

• Operated production equipment following safety and quality procedures.
• Conducted product inspections and identified manufacturing defects.
• Supported production targets while maintaining quality standards.

High School Graduate - Arcelo Memorial National High School