At Telus International, I evaluate and label data for large language models to improve accuracy, safety, and relevance. I also assess search results and AI responses against detailed guidelines, flagging sensitive or harmful content.
At OneForma (Centific), I perform quality checks on AI-generated content and classification tasks. I scored 96% in quality certifications and contributed to the Lightspeed project, checking content accuracy against project requirements.
Before moving into AI evaluation, I assembled aircraft components at Senior BWT Aerospace according to engineering drawings and AS9100 safety standards. My other experience includes operations administration, shipping, fitness coaching, and personal training.
