Bilingual AI Content Evaluator (EN/VN)

Dorado; Northern (KY); Hybrid; USD 23,000 - 32,000; Full time

Job summary

Innodata is seeking detail-oriented evaluators to conduct human quality evaluations for an enterprise AI customer support product on Instagram, WhatsApp, and Messenger. You will review AI interactions against complex rubrics and benchmark queries against authoritative sources.

Experience in customer service and exceptional written English and Vietnamese are essential. Candidates should be comfortable with web-based labeling tools and meet calibration and accuracy targets.

Qualifications

• Customer service background in call centers, retail, or handling customer communications via email, chat, or phone.
• Exceptional written English with strong tone and grammar.
• Exceptional written Vietnamese with appropriate tone and nuance.
• Ability to follow complex evaluation guidelines and rubrics precisely.
• Comfort using web-based labeling tools and interfaces.

Responsibilities

• Evaluate AI-generated customer interactions across dimensions (e.g., action fidelity, faithfulness, hallucination, tone, compliance).
• Benchmark informational and transactional queries against FAQs, product catalogs, and SOPs in the task UI for accuracy.
• Participate in dual-review processes and calibration audits to ensure inter-rater agreement.
• Deliver precise evaluation targets and maintain quality standards.

Skills

Customer service

English proficiency

Vietnamese proficiency

Analytical precision

Tech adaptability

Job description

Innodata is seeking detail-oriented evaluators to conduct human quality evaluations for an enterprise AI customer support product on Instagram, WhatsApp, and Messenger. You will review AI interactions against complex rubrics and benchmark queries against authoritative sources.

Experience in customer service and exceptional written English and Vietnamese are essential. Candidates should be comfortable with web-based labeling tools and meet calibration and accuracy targets.