AI Data Annotator / Technical Domain Evaluator (Freelance)
OtherText
I evaluated AI-generated responses in technical Q&A and account management scenarios, rating outputs for accuracy, helpfulness, tone, and safety. I crafted natural language prompts to test model reasoning and identified issues such as hallucinated facts and off-topic responses. Quality and rubric compliance were maintained through consistent annotation across multiple projects. • Rated and justified the accuracy and quality of AI answers in ICT domains
• Authored prompts to test and surface model weaknesses
• Flagged tone, clarity, and factuality issues for model improvement
• Delivered written feedback to guide AI system refinement
I evaluated AI-generated responses in technical Q&A and account management scenarios, rating outputs for accuracy, helpfulness, tone, and safety. I crafted natural language prompts to test model reasoning and identified issues such as hallucinated facts and off-topic responses. Quality and rubric compliance were maintained through consistent annotation across multiple projects. • Rated and justified the accuracy and quality of AI answers in ICT domains • Authored prompts to test and surface model weaknesses • Flagged tone, clarity, and factuality issues for model improvement • Delivered written feedback to guide AI system refinement
2024 - Present