AI Training & Evaluation Intern
As an AI Training & Evaluation Intern at Scale AI, I evaluated and scored AI-generated responses across benchmarks. I annotated large-scale datasets to support supervised and reinforcement learning workflows. I was involved in prompt testing and cross-functional collaboration to enhance AI model performance. • Evaluated and scored AI-generated outputs for reasoning, factuality, and coherence • Annotated datasets for supervised and RLHF workflows • Conducted prompt testing to optimize responses • Refined evaluation guidelines with team members