RemoteLeads Logo
Sign Up Sign In

Ara Zeta Project - AI Safety Evaluator - Korean (Korea)

3 months, 1 week ago
South Korea
Freelance
Mid Level
AI (Artificial Intelligence)
Artificial Intelligence and Machine Learning
LLM
Apply Now
Welocalize

Welocalize

Welocalize provides translation and localization services to help businesses reach global audiences with precision and efficiency.

Professional Services
1K-5K
Founded 1997
$34M raised
View All Jobs 336

Description

  • Evaluate AI-generated responses using a structured safety rubric.
  • Complete two independent evaluations for each prompt-image pair.
  • Write concise, well-structured rationales in English.
  • Participate in calibration sessions with the project team.
  • Support arbitration when evaluation disagreements occur.
  • Maintain quality and throughput targets during the evaluation period.
  • Document evaluations primarily in English, with some in-language sampling as needed.

Requirements

  • Fluency in the target language and English.
  • Deep cultural understanding of the target locale.
  • Strong written English skills for documentation and rationales.
  • Prior experience in safety evaluation, policy review, content moderation, or rubric-based assessment preferred.
  • Ability to apply detailed guidelines consistently.
  • Strong analytical skills and attention to nuance.
  • Reliable availability during the production window.
  • Comfort working with explicit and sensitive adult material in a professional setting.
  • Priority may be given to candidates with prior prompt-image or similar evaluation experience.

Benefits

  • $22 USD hourly rate.
  • Fully remote freelance engagement.
  • Flexible project-based schedule with 20–40 hours per week.
  • Short-term project duration of 2–3 weeks.
  • Schedule options that allow weekday-only or mixed weekday/weekend availability.
  • Optional access to AI and large language model workshops.
  • Support from a global contributor community with responsive guidance.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

FUTURESEARCH

QA Contractor

FUTURESEARCH Internet Software & Services

FUTURESEARCH is hiring a meticulous quality checker to verify research evaluation tasks used for training and benchmarking frontier AI models.

United States Contract Junior QA Engineer
$156k-$260k
13 hours, 50 minutes ago
Welo Global

Expert Rater Project - Dutch (Netherlands)

Welo Global Professional Services

Welo Data is hiring a Dutch-speaking Expert Rater in the Netherlands to support rater quality, client test rounds, and AI advertising data evaluation on a short-term freelance project.

Netherlands Freelance Junior Manual QA Tester QA Engineer
$58k-$58k
1 day, 13 hours ago
Welo Global

Hydrus -Voice Contributor — English (US)

Welo Global Professional Services

Welo Data is hiring a freelance native-level English (US) speaker to record conversational customer-service audio for a remote AI voice project.

United States Freelance Entry Level AI (Artificial Intelligence) Customer Support
$100k-$100k
1 day, 13 hours ago
Crosslake

AI / ML Consultant

Crosslake 251-1K Capital Markets

Crosslake is hiring a US-based remote consultant to help technology and private equity clients evaluate, improve, and implement AI and software-related initiatives across the investment lifecycle.

United States Contract Lead AI (Artificial Intelligence)
Agile Computer Vision Generative AI LLM Machine Learning MLOps NLP Statistics
1 day, 14 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers