Content Moderator

Global Infovision Private Limited; Hyderabad; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Global Infovision Private Limited in Hyderabad is seeking a GenAI Specialist – Rating to evaluate AI-generated responses against defined quality rubrics. You will assess factuality, grounding, relevance, completeness, safety, and instruction following, with a focus on geographic and Maps/POI information.

The role requires strong analytical skills, excellent English writing and reading comprehension, and a detail-oriented, evidence-based approach to scoring.

Qualifications

• Understanding of Generative AI / LLM behavior.
• Experience with AI response evaluation or data annotation.
• Strong analytical and critical-thinking skills.
• Ability to identify hallucinations and unsupported information.
• Excellent written English and reading comprehension.
• Good geography, navigation, maps, POIs, and local search.
• Strong attention to detail and evidence-based decision making.

Responsibilities

• Evaluate AI-generated responses using quality rubrics.
• Assess factuality, grounding, relevance, completeness, helpfulness, clarity, safety, and instruction following.
• Identify hallucinations, factual errors, and unsupported claims.
• Validate geographic, local, and Maps/POI information.
• Evaluate routes, locations, distances, local businesses, and navigation-related responses.
• Distinguish between minor and critical defects.
• Provide clear, evidence-based justifications for ratings.
• Escalate ambiguous or policy-sensitive cases when required.
• Participate in calibration exercises and maintain consistency across evaluation tasks.
• Provide feedback to improve AI evaluation guidelines and processes.

Skills

Generative AI concepts

AI evaluation & data annotation

Analytical thinking

Hallucination detection

English writing

Geography & maps

Attention to detail

Evidence-based decisions

Tools

Excel/Google Sheets

Jira

SQL basics

Job description

Job title: GenAI Specialist – Rating

Job Location: Hyderabad

Job Type: Full-Time

Key Responsibilities

• Evaluate AI-generated responses using defined quality rubrics.
• Assess factuality, grounding, relevance, completeness, helpfulness, clarity, safety, and instruction following.
• Identify AI hallucinations, factual errors, and unsupported claims.
• Validate geographic, local, and Maps/POI-related information.
• Evaluate routes, locations, distances, local businesses, and navigation-related responses.
• Distinguish between minor and critical defects.
• Provide clear, evidence-based justifications for ratings.
• Escalate ambiguous or policy-sensitive cases when required.
• Participate in calibration exercises and maintain consistency across evaluation tasks.
• Provide feedback to improve AI evaluation guidelines and processes.

Required Skills

• Understanding of Generative AI / LLM behavior.
• Experience or understanding of AI response evaluation, data annotation, content evaluation, or quality analysis.
• Strong analytical and critical-thinking skills.
• Ability to identify hallucinations and unsupported information.
• Excellent written English and reading comprehension.
• Good understanding of geography, navigation, maps, POIs, and local search.
• Strong attention to detail and evidence-based decision-making.

Good to Have

• Experience with AI/LLM evaluation or annotation platforms.
• Search and fact-verification experience.
• Knowledge of local businesses and travel/navigation terminology.
• Basic Excel/Google Sheets skills.
• Basic SQL knowledge.
• Exposure to Jira, documentation tools, or AI evaluation platforms.