Korean AI Safety Model Evaluator

About OpenTrain
OpenTrain is the centralized, open platform where AI training and data-labeling freelancers find work, consolidate opportunities across platforms, and build a unified AI training portfolio they control. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career.

About this role
OpenTrain is recruiting a Korean AI Safety Model Evaluator to help improve the safety of advanced AI systems. You will use Korean language fluency, English communication skills, and cultural judgment to evaluate model behavior around sensitive and dual-use topics. The work combines prompt creation, structured classification, adversarial review, and written justification of safety decisions.

What you will do
Write expert-level prompts in Korean across sensitive subject areas. Apply structured guidelines to classify prompts and conversations. Identify adversarial phrasing, escalation patterns, and other safety concerns. Document the reasoning behind evaluation judgments clearly and consistently. Apply cultural and linguistic context when assessing how sensitive topics are handled.

Required skills
Candidates must have native or near-native Korean fluency and business-level written English. They must be able to document evaluation reasoning in business-level written English, demonstrate strong written reasoning and close attention to detail, and exercise sound judgment when working with sensitive and dual-use information. A bachelor's degree, completed or in progress, is required.

Helpful background
Experience reviewing, grading, or red-teaming written or technical content is useful. Background in trust and safety, content moderation, policy evaluation, or adversarial testing can help with assessing model behavior and identifying escalation risks. Previous AI or machine learning experience is not required.

Schedule, location, and pay
This is remote contractor work with an expected commitment of approximately 7 hours per week. Applicants based in East Asia are preferred, but applicants elsewhere are welcome. The rate is $48‑$52 per hour, and the project can start immediately.

Why work with OpenTrain
OpenTrain gives freelancers one place to manage AI training opportunities instead of rebuilding proof of work on every platform. A stronger OpenTrain profile helps you show credible experience, discover roles that match your skills, and turn AI training and data-labeling work into a long-term portfolio.