Remote opportunity for Dutch and English bilingual professionals to perform transcription, annotation, audio evaluation, rubric development, and AI model benchmarking for leading AI research projects.
Argentinian Spanish Audio Generalist Evaluator Expert
United Kingdom, United States
$50 – $50/hr
June 11, 2026
Reposted Jun 11
Originally posted February 12, 2026.
Job description
Mercor is seeking an Argentinian Spanish Audio Generalist Evaluator Expert to contribute to a high-impact AI research project focused on audio understanding, transcription, annotation, and model evaluation.
This role supports the training and benchmarking of advanced language models by transforming audio and video content into accurate, structured text and evaluating AI-generated outputs against rigorous quality standards.
The position is ideal for bilingual professionals with strong analytical, writing, and language skills who are fluent in Argentinian Spanish and English.
Key Responsibilities
Transcribe and Optimize Audio & Video
- Listen to and analyze audio and video content in Argentinian Spanish
- Produce accurate transcriptions following detailed project requirements
- Create high-quality written outputs in Spanish and English when required
- Ensure strict compliance with formatting, style, and quality standards
Define and Document Evaluation Standards
Establish expectations for high-quality responses in consumer audio contexts
Create evaluation rubrics and grading guidelines
Document standards in both:
- Spanish (Argentina)
- English
Maintain consistency across reviewers and evaluation tasks
Conduct Model Testing and Grading
Run prompts through language models
Evaluate AI-generated outputs for:
- Accuracy
- Completeness
- Instruction following
- Clarity
Apply predefined evaluation criteria consistently
Support Benchmarking and Quality Assurance
- Participate in review and QA workflows
- Validate datasets before benchmark integration
- Collaborate with project leads to improve task design and resolve ambiguities
- Help maintain high-quality evaluation standards across the project
Minimum Qualifications
Strong:
- Writing skills
- Editing skills
- Critical thinking abilities
Fluency in:
- Spanish (Argentina)
- English
Ability to work independently and meet deadlines
Availability of 10–20 hours per week
Preferred Qualifications
College student or recent graduate
Background in:
- Linguistics
- Humanities
- Social Sciences
- Technical disciplines
Experience with:
- Transcription
- Annotation
- Evaluation workflows
- Research projects
Interest in:
- Artificial Intelligence
- Language Models
- Applied Research
Application Process
- Complete a short AI-led interview (approximately 15 minutes)
- Successful candidates will be onboarded and invited to project work
Additional Information
- Fully remote work
- Flexible schedule
- Weekly payments via Stripe or Wise
- Opportunity to gain hands-on experience with frontier AI research and evaluation systems
About Mercor
Mercor partners with leading AI labs and enterprises to train and evaluate frontier AI systems using human expertise.
Contributors work alongside researchers to help improve the next generation of AI models through high-quality evaluation and training data.
Apply now
You will be redirected to the company's website to complete your application.
Native/near-native Nepali and English speakers to transcribe Nepali video content, annotate timestamps, analyze emotional tone, and conduct grammar and syntax analysis for AI training. Minimum 15 hours/week.
Join the CrowdGen team as an Independent Contractor for Project Vistula ! We are currently looking for Independent Contractors who are native German speakers with strong English proficiency and a strong background in language expertise .
Join the Appen team as an Independent Contractor for Project Centric . Project Centric is seeking individuals for an ongoing, ad-hoc project focused on improving AI-powered translation.