AI Content Trainer & Evaluator (Freelance)
As an AI Content Trainer & Evaluator, I performed RLHF tasks to train and refine Indonesian Large Language Models. My responsibilities included evaluating AI-generated responses for accuracy and safety. I also conducted transcription and voice model quality control tasks. • Trained LLMs using RLHF ranking, rating, and qualitative judgment. • Evaluated AI outputs for truthfulness and sound logic. • Identified AI model errors and hallucinations in responses. • Transcribed and quality-controlled Indonesian audio data.