Technical AI Evaluator (Contract)
Collaborated with Machine Learning Engineers to refine labeling taxonomies and align annotation outputs with key model performance KPIs. Performed rigorous evaluations and feedback cycles for LLMs, emphasizing reduction of hallucinations in logical reasoning tasks. Authored technical documentation and SOPs to standardize annotation and quality across teams. • Evaluated alternative data-weighting perspectives supporting project pivots. • Conducted model performance assessments to improve logical output integrity. • Wrote visual reports using productivity toolkits to communicate annotation results. • Standardized processes for high-quality annotation output.