Uchenna Chima

Ai Trainer @Mercor

Toronto, ON, CA

Performed daily preference ranking of hundreds of multimodal AI outputs (images, audio, and video) against prompts to evaluate model performance and alignment, supporting reinforcement learning from human feedback (RLHF)- Applied systematic comparative judgment techniques to assess relevance, quality, and coherence of generative model outputs, ensuring consistent evaluation across diverse modalities- Maintained high accuracy and throughput in large-scale annotation workflows, contributing to reliable training data for model fine-tuning and preference optimization- Utilized specialized labeling platforms and guidelines to deliver precise annotations that strengthened preference-based reinforcement learning pipelines.

Linsly School

High School Diploma

Dalhousie University

Masters of Applied Computer Science, Computer Science

University of South Florida

Bachelor of Science, Computer Science