Senior QA Engineer — AI/LLM model testing and evaluation (PwC)
Conducted AI/LLM model testing and evaluation using predefined quality metrics. Assessed model responses for accuracy, relevance, source document coverage, and response variability against evaluation criteria. Documented evaluation results as part of the quality assurance workflow for software and AI-enabled outputs. • Evaluated accuracy and factual correctness of model responses. • Assessed relevance of responses to prompts or requirements. • Measured source document coverage and response variability. • Used quality metrics defined for the evaluation process.