AI Prompt Evaluator & QA Specialist (Remote Contract)
Served as an AI Prompt Evaluator & QA Specialist, reviewing AI-generated prompts and responses against project QA rubrics. Performed RLHF preference ranking by comparing multiple candidate responses and selecting the best option per guidelines. Wrote concise, constructive rationales to justify preference choices for reward model training. • Reviewed correctness, clarity, safety, and factual accuracy • Conducted response-pair comparisons for preference ranking • Maintained inter-batch consistency via calibration to gold tasks • Performed content safety analysis and basic bias detection