About this role
Role Overview:
In the role of AI Quality Analyst, you will play a crucial part in evaluating a new personalization feature for Gemini. Your primary responsibility will be to assess how effectively the model utilizes information from your previous interactions on Gemini, Gmail, Google Search, and YouTube to enhance the relevance and helpfulness of its responses. This position demands a unique combination of creativity and analytical skills, as you will design prompts based on your personal experiences and rigorously analyze the quality of the model''s personalized responses, focusing on aspects such as Grounding, Integration, and Helpfulness.
Key Responsibilities:
- Design and execute multi-turn conversational prompts (typically 1-5 turns) that require the AI to leverage your personal information and experiences.
- Evaluate model responses against your intent from the starting prompt, ensuring appropriate application of personalization.
- Analyze responses for Grounding issues, verifying that claims about you are supported by evidence rather than flawed inferences or hallucinations.
- Assess Integration quality to ensure personal data is naturally woven into responses without robotic overnarrating.
- Conduct rigorous evaluations and stack-rank two model responses side-by-side to determine which is more helpful, user-friendly, and enjoyable.
Qualifications:
- Korean Proficiency: High degree of reading and writing ability in Korean, as it is the focus language for this project.
- Personal Account Usage: Willingness to use your primary personal Google account (not a testing account) and enable personal data sources for genuine assessment.
- Schedule Flexibility: Full-time availability in your local time zone is required, as we are staffing a global, 24-hour operations team.
- Exceptional Analytical Thinking: Ability to evaluate nuanced and ambiguous AI responses, particularly in assessing personalization quality.
- Creative Prompt Engineering: Experience in designing creative, multi-turn starting prompts based on personal context to thoroughly test the model''s capabilities.
- Strong Evaluation Acumen: Understanding of personalization concepts, including the ability to identify incorrect personalization, poor inferences, and forced connections.
- Meticulous Attention to Detail: Capability to review Side-by-Side (SxS) model responses and spot subtle differences in naturalness and overnarrating.
- Excellent Written Communication: Ability to write clear, concise, and structured rationales for model rankings, explicitly referencing specific turn numbers.
- Feedback: Ability to provide constructive feedback and detailed annotations.
- Communication: Excellent communication and collaboration skills.
- Independence: Self-motivated and able to work independently in a remote setting.
- Technical Setup: Desktop/Laptop set up with a reliable internet connection.
Work Terms:
Contract position with full-time availability required.
Compensation:
$15/hour.
Eligibility:
Must be able to work remotely and have access to a personal Google account for assessment purposes.