AIWorkJobs
Turing logoTuringPlatform listing

AI Quality Analyst (Gemini) - Chinese

Evaluate Gemini's personalized Chinese responses for relevance and accuracy.

Remote · Eligibility not specifiedContract
Work arrangement
Remote
Eligibility
Eligibility not specified
Engagement
Contract
Compensation
$15/hr
Specialty
AI Training

About the role

Assess how Gemini uses a person’s conversation history, Gmail, Google Search, and YouTube activity to personalize Chinese responses. You’ll create multi-turn prompts based on personal context, compare model answers, and document issues with grounding, relevance, and helpfulness. The contractor engagement lasts 3 months and requires at least 4 hours a day, up to 40 hours per week, with 4 hours of overlap with PST.

What you would do

  • Create and run personal-context prompts, typically spanning 1 to 5 turns, to test Gemini’s personalization.
  • Check whether claims about the user have evidence, and flag faulty inferences, unsupported details, or hallucinations.
  • Compare and rank two model responses based on helpfulness, ease of use, and user experience.
  • Assess responses for grounding, integration of personal context, and helpfulness.
  • Identify differences in naturalness and over-narration between responses.
  • Write clear rationales that support each ranking and cite specific conversation turns.
  • Review model debug information to confirm that chat summaries and data sources were used.
  • Delete evaluation conversations to keep them out of future chat history.
  • Provide detailed annotations and constructive feedback.

Requirements

  • Read and write Chinese at a high level; Chinese is the project’s focus language.
  • Design creative, multi-turn prompts grounded in personal context.
  • Recognize incorrect personalization, weak inferences, and forced connections.
  • Compare side-by-side responses and spot subtle differences in naturalness and over-narration.
  • Write clear, concise rationales that cite specific conversation turns.
  • Hold a BS or BA degree in a relevant field, or have equivalent experience.
  • Commit at least 4 hours per day and up to 40 hours per week.
  • Provide 4 hours of overlap with PST.

Preferred qualifications

The source marks these as preferred, not required.

  • Experience in data annotation, AI quality evaluation, content moderation, or a related role.

Who should apply

Candidates with strong written Chinese and experience crafting contextual prompts can assess whether Gemini’s personalized answers are grounded and useful. A background in an analytical field, plus experience reviewing AI or annotated content, fits the work.

How applying works on Turing

Create a profile, finish any required proctored assessments, then complete screening or a role interview.

  1. Apply through work.turing.com and complete your profile.
  2. Finish the required proctored assessments for the role.
  3. Complete shortlisting, screening, or a technical interview.
  4. Confirm rate, availability, and eligibility before an offer.

Typical timeline: Review takes 48 hours to six weeks after all required steps; consideration replies are usually within 12 hours.

Paid steps: Not stated by the source

Not every role requires tests. Turing does not review an application until required assessments are complete.

Process checked Nov 19, 2026. AIWorkJobs does not submit applications or charge a fee. Read the full Turing process and its official source on the Turing page.

Skills mentioned by the source

  • chinese
  • gemini
  • prompt engineering
  • ai evaluation
  • data annotation
  • content moderation
  • personalization evaluation
  • response ranking
  • grounding analysis
  • conversation analysis
  • gmail
  • google search
  • youtube
  • business analysis
  • content creation

Listing reference: ai-quality-analyst-gemini-chinese-62134. Source: Turing. If something here contradicts the source, the source controls. Report a correction.

Related roles

Other work on the index.

See more in this category

Turing

AI Quality Analyst - English

Evaluate AI personalization quality using your personal experiences and insights.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Contract
Compensation
Pay not listed
  • ai evaluation
  • personalization evaluation
  • prompt engineering
Quality Assurance & TestingView job

Turing · via Braintrust

AI Evaluator – Education (Experienced Gemini Users)

Help assess and improve AI responses through research, fact-checking, logic analysis, and educational evaluation. The role suits students and working professionals who use the Gemini App for learning. Work remotely from the United States for an expected 16-week project, with a possible extension. Plan for at least 20 hours per week, up to 40 as project needs change, and four hours of overlap with Pacific working hours.

Location and eligibility
Remote · United States only
Engagement type
Contract
Compensation
$20/hr
  • gemini app
  • research
  • fact-checking
AI evaluationView job

SME Careers

English Language Expert

Review AI-generated English responses or create language examples that show sound reasoning and clear, correct writing. You will judge accuracy, prompt fit, and meaning, then explain edits or compare candidate responses. The work draws on English grammar, discourse analysis, and tools such as ChatGPT, Gemini, and Perplexity. This remote contract role requires at least C1 English proficiency and a relevant bachelor’s degree.

Location and eligibility
Remote · Eligible in 27 countries
Engagement type
Contract
Compensation
Up to $25/hr
  • english
  • copyediting
  • discourse analysis
Language & LinguisticsView job

AfterQuery

Mandarin Research Reviewer

Reviewers help improve an AI research tool that turns complex questions into structured tables. You will check Mandarin-language research results against primary sources, assess each entry for accuracy and completeness, and search for missing information. The remote, project-based work is asynchronous and self-paced, with an expected commitment of 10–20 hours per week over the next several weeks. Each task takes about 1.5–2 hours.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Not specified
Compensation
$30/hr
  • mandarin chinese
  • web research
  • source verification
AI evaluationView job