Freelance AI Data Trainer (Various)
Freelanced with AI training sites to evaluate large language models (LLMs) on their capabilities using structured testing workflows. Performed side-by-side comparisons of model outputs and assessed response quality as part of an LLM evaluation process. Conducted A/B prompt testing to determine which prompts produced better results for the given tasks. • Side-by-side LLM output evaluations • A/B prompt testing • Capability testing across multiple prompts • Quality assessment/rating of responses