We are sharing a specialised part-time consulting opportunity for detail-oriented professionals with strong Romanian language skills, transcription ability, critical thinking, and high-quality written communication.

This role supports an exciting collaboration with a leading frontier AI research laboratory focused on improving advanced audio and multimodal AI systems through structured evaluation, transcription, annotation, and benchmarking workflows.

Selected professionals will listen to and transcribe audio, annotate images, evaluate videos, and help develop high-quality evaluation standards for audio-related consumer tasks. This opportunity is especially well-suited to professionals with strong academic backgrounds and a talent for producing clear, well-structured written work that supports advanced AI model training and assessment.

Key Responsibilities

Professionals in this role may contribute to:

Audio & Video Transcription and Evaluation
Listen to and transcribe audio content from Romanian with multiple constraints and instructions
Evaluate videos and annotate images to support multimodal AI training workflows
Help ensure that outputs are accurate, detailed, and aligned with project requirements

Rubric Development & Evaluation Standards
Define high-level expectations for correct responses in general audio consumer contexts
Develop comprehensive rubrics and structured evaluation criteria
Help create clear standards for how model outputs should be assessed across varied tasks

Model Testing, Benchmarking & QA Support
Run prompts through models and assess preliminary outputs against expectations
Support benchmarking and quality assurance processes before tasks are integrated into official benchmarks
Help maintain consistency, rigor, and reliability across evaluation workflows

Ideal Profile

Strong candidates may have:
Strong Romanian language skills with the ability to accurately transcribe and review audio content
Strong writing and critical thinking skills
A BS or BA from a reputable institution, completed or in progress
Comfort working with structured evaluation guidelines and quality-focused workflows
A detail-oriented and reliable approach to transcription, assessment, and written analysis

Preferred qualifications

College student or graduate status
Experience with transcription, annotation, content evaluation, or rubric writing
Comfort working across audio, image, and video evaluation tasks
Ability to produce clear, well-structured written judgments and evaluation criteria

Why This Opportunity

Contribute specialised Romanian language and evaluation expertise to a cutting-edge AI collaboration
Help improve advanced audio and multimodal AI systems through rigorous transcription and benchmarking work
Work on high-impact evaluation and QA workflows with leading AI researchers
Flexible project-based work with structured expectations and competitive hourly compensation

Contract Details

Independent contractor role
In-person role based in SF, USA or London, UK
Hourly compensation of $25–$50 per hour
Minimum commitment of 20 hours per week
Approximate project length of 2–4 weeks
Projects may be extended, shortened, or concluded early depending on project needs and performance
Weekly payments via Stripe or Wise
Work will not involve access to confidential or proprietary information from any employer, client, or institution
Please note: We are unable to support H1-B or STEM OPT candidates at this time
Start date: Immediate

About the Platform

This opportunity is available through a leading AI-driven work platform that connects domain experts with frontier AI research projects.

Experts contribute to improving advanced AI systems by providing specialised expertise across real-world workflows, structured evaluation, model training support, and domain-specific content validation.

By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy: https://www.24-mag.com/privacy-policy