Worked on multiple AI training and evaluation projects involving prompt engineering, response comparison, data classification, and social media annotation. Contributed to improving AI model performance by creating and refining prompts using RLHF (Reinforcement Learning from Human Feedback), evaluating and selecting the best responses through A/B testing, and accurately labeling data based on defined guidelines.
Performed content analysis on social media data to identify sentiment, intent, and policy compliance, ensuring high-quality annotations for content moderation systems. Maintained consistency, attention to detail, and adherence to project guidelines while handling diverse datasets.
1
5