Remote Hindi AI Personalization QA Specialist

Hired; Indonesia; Remote; IDR 1,057,455,000 - 1,762,425,000; Full time

Job summary

Hired is hiring an AI Quality Analyst (Personalization) to evaluate a new personalization feature for an advanced AI model, with a focus on Hindi language performance. The role analyzes how past conversations, email, search and video activity influence responses, and requires prompt design and precise evaluation.

The analyst will assess grounding, integration and helpfulness across multi-turn interactions, and provide actionable feedback while upholding data privacy and remote collaboration for

Qualifications

• Proficiency in reading and writing Hindi.
• Experience evaluating AI-generated content, especially in personalization.
• Ability to design creative prompts for testing AI models.
• Strong attention to detail for nuanced responses.
• Willingness to use a personal Google account with data sources for evaluation.
• Familiarity with AI personalization, grounding, and user intent alignment.
• Experience in multi-turn conversation analysis and response evaluation.
• Comfort with data privacy considerations when handling personal user information.
• Ability to work full-time with flexibility for a global 24-hour operations team.

Responsibilities

• Design and refine multi-turn prompts to test personalization capabilities.
• Evaluate AI responses for grounding, integration, and helpfulness.
• Identify incorrect personalization or flawed inferences in outputs.
• Compare side-by-side model responses to assess consistency.
• Provide detailed feedback on alignment with user context and intent.

Skills

Hindi proficiency

Analytical evaluation

Prompt design

Attention to detail

Google account data access

AI personalization concepts

Multi-turn analysis

Data privacy

Full-time flexibility

Job description

Hired is hiring an AI Quality Analyst (Personalization) to evaluate a new personalization feature for an advanced AI model, with a focus on Hindi language performance. The role analyzes how past conversations, email, search and video activity influence responses, and requires prompt design and precise evaluation.

The analyst will assess grounding, integration and helpfulness across multi-turn interactions, and provide actionable feedback while upholding data privacy and remote collaboration for