Remote AI Quality Analyst (Thai)

About the Company

Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing accelerates frontier research with high-quality data, advanced training pipelines, and AI researchers across coding, reasoning, multilinguality, multimodality, and agents, and helps enterprises deploy reliable AI systems that deliver measurable impact.

About the Role

As an AI Quality Analyst, you will evaluate a new personalization feature for Gemini by assessing how well the model uses information from your past Gemini conversations, Gmail, Google Search, and YouTube activity to make responses more relevant and helpful. The role combines creative prompt design and analytical evaluation of personalized model responses across dimensions like grounding, integration, and helpfulness.

Responsibilities

• Design and execute multi-turn conversational prompts (typically 1–5 turns) that require the AI to utilize your personal information and experiences.
• Evaluate model responses based on the intent of the starting prompt and check whether personalization was appropriately applied.
• Analyze responses for grounding issues to ensure claims about you are supported and not incorrect inferences or hallucinations.
• Assess integration quality to ensure personal data is woven naturally into responses without robotic overnarrating.
• Rigorously evaluate and stack-rank two model responses side-by-side (SxS) to determine which is more helpful, easy to use, and enjoyable.
• Write clear, defensible rationales for comparisons, explicitly referencing specific turn numbers and extracting/verifying debug info to confirm chat summaries and data sources were used.
• Maintain strict data hygiene by deleting evaluation conversations to prevent them from polluting future chat history.

Qualifications

• Thai proficiency: ability to read and write in Thai with a high degree of comprehension, as Thai is the focus language for this project.
• Willingness to use your primary personal Google account and enable personal data sources for a genuine assessment.
• Full-time availability in your local time zone; the team staffs global, 24-hour operations.
• Exceptional analytical thinking with ability to evaluate nuanced and ambiguous AI responses and assess personalization quality.
• Experience designing creative, multi-turn starting prompts based on personal context to thoroughly test model capabilities (creative prompt engineering).
• Strong evaluation acumen and understanding of personalization concepts, including identifying incorrect personalization, poor inferences, and forced connections.
• Meticulous attention to detail and ability to review side-by-side model responses and spot subtle differences in naturalness and overnarrating.
• Excellent written communication with ability to write clear, concise, and structured rationales referencing specific turns.
• Ability to provide constructive feedback and detailed annotations, strong communication and collaboration skills, and ability to work independently in a remote setting.
• Technical setup: desktop or laptop with a good internet connection.
• BS/BA degree or equivalent experience in a relevant field (e.g., Policy, Law, Ethics, Linguistics, Journalism, Computer Science) or equivalent experience.
• Experience in data annotation, AI quality evaluation, content moderation, or related roles is strongly preferred.

Additional Information

• Engagement type: contractor.
• Engagement length: 3 months.
• Commitments required: at least 4 hours per day and minimum 30 hours per week, with 4 hours of overlap with PST. Two options of time commitment: 30 hrs/week or 40 hrs/week.
• After applying, you will receive an email with a login link to access the portal and complete your profile.