Job Description
Evaluate, score, and provide feedback on AI responses to ensure accuracy, relevance, and cultural appropriateness, playing a critical part in helping to train safe, useful AI. You will evaluate model outputs through A/B testing, ranking, scoring, and annotation. You’ll suggest improvements and corrections using natural language examples and flag content with safety concerns (e.g., toxicity, hallucinations, or policy violations). Please note: You will be exposed to prompts that may include sexual, political, violent, or otherwise offensive content.
About RWS
RWS embraces DEI and promotes equal opportunity; the company is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind.