Job Description
In this role, you will evaluate, score, and provide feedback on AI responses to ensure accuracy, relevance, and cultural appropriateness. You’ll play a critical part in helping to train safe, useful AI. You will be exposed to prompts that may include sexual, political, violent, or otherwise offensive content . Candidates must be comfortable reviewing such material.
Responsibilities include: Review and score AI-generated responses across a wide variety of topics, suggest improvements and corrections using natural language examples, evaluate model outputs through A/B testing, ranking, scoring, and annotation, and flag content with safety concerns (e.g., toxicity, hallucinations, or policy violations).
About RWS
RWS embraces DEI and promotes equal opportunity, we are an Equal Opportunity Employer and prohibit discrimination and harassment of any kind.