Remote Hindi Language Evaluator for AI Training

micro1; United States; Remote; USD 41,000 - 90,000; Full time

Benefits offered by this job

Remote work

Job summary

micro1 is a data lab that helps AI labs and enterprises train foundational models and agents. We provide frontier evaluations and reinforcement learning environments to improve LLM capabilities, as well as contextual evaluations to monitor and improve AI agents in enterprise settings. Role: Hindi Bilingual Expert (Contractor).

Location: Remote. You will evaluate Hindi audio for nativeness and fluency, provide English feedback, and document justifications to guide model learning and evaluation

Qualifications

• Native-level proficiency in Hindi with clear enunciation.
• Minimum B2 level proficiency in English.
• Background in voice specialization, linguistics, phonetics, or related field preferred.

Responsibilities

• Listen to audio clips in Hindi and evaluate nativeness and fluency of the speaker or model output.
• Assess pronunciation, intonation, and linguistic authenticity according to guidelines.
• Document assessments with clear written English feedback noting key linguistic factors.
• Provide detailed justifications for each evaluation to ensure clarity and consistency.
• Collaborate with project coordinators to clarify requirements or address ambiguities.
• Contribute insights to help improve AI model performance in Hindi language understanding and generation.
• Ensure timely and accurate completion of audio review tasks with high quality.

Skills

Hindi

Voice Recording

Audio Recording

Job description

micro1 is a data lab that helps AI labs and enterprises train foundational models and agents. We provide frontier evaluations and reinforcement learning environments to improve LLM capabilities, as well as contextual evaluations to monitor and improve AI agents in enterprise settings. Role: Hindi Bilingual Expert (Contractor).

Location: Remote. You will evaluate Hindi audio for nativeness and fluency, provide English feedback, and document justifications to guide model learning and evaluation