Technical RLHF Specialist & AI Evaluation Engineer (Freelance)
As a Technical RLHF Specialist and AI Evaluation Engineer, I conducted Reinforcement Learning from Human Feedback (RLHF) on Large Language Models by Anthropic. My responsibilities included rigorous evaluation of AI-generated code and logical reasoning outputs, focusing on accuracy and edge-case handling. I developed structured testing parameters to improve the reliability of LLMs in technical tasks. • Evaluated and scored LLM outputs related to software engineering scenarios. • Validated security, logic, and accuracy in AI-generated computer code. • Designed procedures to reduce hallucinations in technical problem-solving contexts. • Contributed to iterative improvement of model performance and reliability.