Data Evaluator
Worked as a Data Evaluator focusing on AI model response assessment and ranking (RLHF-based workflows). Reviewed and evaluated large volumes of text outputs for accuracy, logical consistency, instruction adherence, and overall response quality. Conducted side-by-side comparisons of multiple AI-generated responses and provided structured justifications for rankings. Identified hallucinations, factual inaccuracies, and reasoning flaws across general knowledge, finance, and technical domains. Applied detailed annotation guidelines and maintained high consistency across tasks. Demonstrated strong analytical thinking, attention to detail, and efficiency while handling repetitive evaluation tasks at scale. Contributed to improving model performance through high-quality feedback and scoring.