Business Analyst (LLM Training)
As a Business Analyst (LLM Training) at Turing, I performed side-by-side evaluations of large language model (LLM) outputs, assessing their quality, accuracy, and relevance. I conducted fact-checking and quality validation to identify inconsistencies and provided structured justifications for each evaluation. This role required following established guidelines for evaluating LLM responses and maintaining high standards of output assessment. • Performed prompt evaluation and output comparison of LLM-generated text. • Responsible for reviewing and annotating model answers for hallucination detection. • Ensured high-quality data annotation and strict adherence to QA processes. • Utilized internal/proprietary tooling for annotation and assessment tasks.