A complete application in a minute
Tailored resume and cover letter, ready to send.
Turing seeks US-based generalist raters to support Gemini Personalization Evals, evaluating AI responses across Google apps using personal email history and business activity as context.
You will assess relevance, accuracy and personalization, compare responses, and provide well-reasoned feedback while upholding strict data privacy and confidentiality throughout the project.
We are seeking US-based generalist raters to participate in Gemini Personalization Evals. In this role, raters will perform generalist evaluation work using personalized prompts designed to retrieve context and data across connected Google apps. In this role, you will be part of a team responsible for evaluating the quality of personalized AI interactions for business users. Your day-to-day responsibilities will include: Evaluating AI-generated responses based on your professional email history and business account activity. Assessing whether responses are relevant, accurate, helpful, and appropriately personalized. Identifying issues related to incorrect personalization, unsupported assumptions, or irrelevant recommendations. Comparing multiple AI responses and determining which provides the better overall user experience. Providing clear, detailed, and well-reasoned evaluation feedback to support model improvements. Following project guidelines to ensure consistent, accurate, and high-quality evaluations. Maintaining data privacy and adhering to all project confidentiality requirements throughout the evaluation process.
Required skills: Domain-Specific Languages Location: Must be currently based in the United States. App Connectivity: Must be willing and able to connect their Google apps (e.g., Gmail, Google Photos, Google Calendar, Google Drive, etc.) to Gemini to support data retrieval and personalized prompt evaluations. Role Scope: Perform generalist rating and evaluation tasks, assessing model performance, context retrieval, and response quality across connected apps. Account Activity: Active use of standard Google workspace/consumer apps with sufficient personal data/history to generate and evaluate retrieval prompts. Exceptional Analytical Thinking: Ability to evaluate nuanced AI responses and identify strengths and weaknesses in personalization quality. Attention to Detail: Strong ability to review AI-generated responses and identify subtle issues or inconsistencies. Communication: Excellent written communication skills for providing clear and structured evaluation feedback. Independence: Self-motivated and able to work independently in a remote environment.