AI Training Specialist
As an AI Training Specialist at DataAnnotation Tech, I conducted RLHF tasks to improve large language models' performance in computer science domains. I focused on training, auditing, and refining models using high-level technical prompts, ensuring accuracy and adherence to coding standards. I created gold standard responses, analyzed model reasoning, and addressed hallucinations and logic errors. • Trained LLMs with advanced topics such as dynamic programming and systems architecture. • Audited and refined AI-generated Python and C++ code to comply with style guides. • Designed gold standard reference responses, boosting debugging accuracy in edge cases. • Evaluated model logic using chain-of-thought analysis to minimize technical fallacies.