Shital M.

I have over 3+ years of experience in AI Evaluation and related technical work, spanning prompt engineering, RLHF, rubric-based evaluation, and quality-check level review of AI model outputs. My work has included designing and evaluating prompts across benign, harmful, red-teaming, and jailbreak scenarios. Ranking and rating AI responses for helpfulness, accuracy, safety, and instruction-following; designing and applying scoring rubrics (1–5 scale) across factual accuracy, completeness, and clarity; conducting quality-check level reviews and providing detailed feedback on contributors' evaluation work; and multilingual dataset annotation and review across Hindi, Gujarati, and English.