Yusuf T.

Key Skills

Freelancer Overview

I do not have direct experience applying post-training techniques to large language models. However, I have experience evaluating AI outputs, identifying factual inaccuracies, verifying information through research, and assessing responses for instruction-following and reliability. From an evaluation perspective, I have observed that clear task definitions, high-quality training data, accurate labeling, and consistent feedback are critical for improving model performance. I am particularly interested in AI evaluation and data annotation, and I am eager to deepen my understanding of model training and alignment methodologies.

Education

Work History