Omedaro Victor-olubumoye

Key Skills

Software

Telus

Top Subject Matter

No subject matter listed

Top Data Types

Document

Image

Text

Video

Top Task Types

Evaluation/Rating

Prompt + Response Writing (SFT)

Question Answering

Text Generation

Freelancer Overview

I have hands-on experience in AI model evaluation and data annotation, where I assess AI outputs for relevance and quality, perform prompt–response evaluations, and design rubrics to compare model performance. My work involves identifying strengths, weaknesses, and failure points in AI models, as well as providing structured feedback to drive model improvement. I am skilled in using AI tools like ChatGPT, Canva AI, and CapCut AI, and have contributed to research on responsible AI use, algorithmic bias, and digital inclusion. My background also includes building and managing digital communities, observing creator interactions with AI tools, and supporting ethical, effective AI adoption, particularly in developing regions.

Labeling Experience

AI Model Evaluation & Data Annotation – Outlier, TELUS International

TelusTextEvaluation Rating

Evaluated AI model outputs for relevance and quality using established, task-specific rubrics. Conducted data annotation through prompt–response evaluation and relevance judgment tasks. Designed and tested prompts as well as rubrics to compare and assess AI model behaviors. • Provided structured feedback on model strengths and weaknesses. • Identified points of model failure through systematic output testing. • Supported model improvement with targeted evaluation insights. • Collaborated with AI teams in model assessment and annotation processes.

Evaluated AI model outputs for relevance and quality using established, task-specific rubrics. Conducted data annotation through prompt–response evaluation and relevance judgment tasks. Designed and tested prompts as well as rubrics to compare and assess AI model behaviors. • Provided structured feedback on model strengths and weaknesses. • Identified points of model failure through systematic output testing. • Supported model improvement with targeted evaluation insights. • Collaborated with AI teams in model assessment and annotation processes.

2024

Education

Work History