LLM Content Evaluator & Support Benchmark Specialist

Innodata Inc.; Chile; Presencial; CLP 6.000.000 - 9.000.000; Jornada completa

Descripción de la vacante

Innodata Inc. is seeking detail-oriented Content Evaluators to test, review, and benchmark AI-generated customer support interactions across major platforms.

You will evaluate outputs against strict rubrics and knowledge bases to help improve AI model quality, accuracy, and tone. Responsibilities include reviewing conversations for accuracy and tone, verifying against FAQs and SOPs, and participating in calibration sessions to ensure consistency.

Formación

• Minimum of a Bachelor's Degree in any discipline.
• Native or professional proficiency in Spanish, along with excellent written English skills.

Responsabilidades

• Evaluate AI outputs: review and score AI-generated customer support conversations for accuracy, tone, compliance, faithfulness, and correct agent handoff.
• Fact-checking & verification: verify customer intents and factual responses against business FAQs, product catalogs, SOPs, and official docs to detect hallucinations or errors.
• Quality & alignment: participate in dual-review sessions and daily calibration audits to maintain high scoring consistency.
• Timely delivery: complete assigned evaluations accurately within the project's required turnaround time (TAT).

Conocimientos

Detail-oriented

Spanish proficiency

English writing

Educación

Bachelor's Degree

Descripción del empleo

Innodata Inc. is seeking detail-oriented Content Evaluators to test, review, and benchmark AI-generated customer support interactions across major platforms.

You will evaluate outputs against strict rubrics and knowledge bases to help improve AI model quality, accuracy, and tone. Responsibilities include reviewing conversations for accuracy and tone, verifying against FAQs and SOPs, and participating in calibration sessions to ensure consistency.