LLM Post-Training Intern
Contributed to post-training evaluation of Large Language Models (LLMs) to enhance their response accuracy and relevance. Assisted the team in annotating and preprocessing text data according to defined quality metrics. Utilized prompt engineering techniques to improve model outputs and ensure adherence to correctness standards. • Evaluated LLM-generated answers for clarity, accuracy, and appropriateness. • Annotated and categorized textual data for model refinement workflows. • Collaborated with AI research staff to optimize model assessment protocols. • Acquired hands-on experience in LLM post-training and evaluation environments.