Technical Data Annotator / RLHF Specialist (Freelance)
Engaged in Reinforcement Learning from Human Feedback (RLHF) annotation tasks focused on code and prompt evaluation. Used technical fluency in code and logical reasoning to rank, correct, and explain outputs for AI model alignment. Provided high-quality feedback to support fine-tuning of language models handling complex programming tasks. • Performed RLHF ranking and evaluation for AI-generated code and explanations. • Used Python and web-based tools for annotation workflows and QA. • Applied debugging and code correctness assessment to labeling tasks. • Contributed to Chain-of-Thought prompting and structured prompt evaluation for AI models.