Content Quality and Evaluation Specialist (Mandarin Speaking) - Safety Model Operations

Written by the T&S Network from TikTok's posting.

Quality assurance and evaluation work for the machine learning models that flag harmful content on TikTok, sitting in the Safety Model Operations team. The role builds and maintains the Golden Sets, which are the ground-truth labeled data used to judge platform safety policies, AI model evaluation and enforcement teams, and works on the labeling accuracy the automated safety systems depend on.

What you'd do

• Build and iterate Golden Sets by curating long-tail, high-risk and complex edge cases as ground truth.
• Run deep-dive analyses on high-risk and heavily debated cases to find patterns of policy misapplication.
• Turn macro policies into executable SOPs and operational guidelines.
• Work with Operations, Algorithm and Product teams to find system weak points using Golden Set metrics.
• Set up daily quality assurance mechanisms and a content quality management framework.
• Track and attribute data metrics to improve accuracy and operational efficiency.

What it asks for

• Several years working in internet Trust & Safety, QA, AI data evaluation or policy operations.
• Strong logical reasoning and ability to find root causes in ambiguous business scenarios.
• Working-level fluency in English for professional use.
• Mandarin proficiency, required for daily liaison with the China team.
• Extreme attention to detail and consistency in standards.
• Understanding of machine learning logic and data labeling frameworks (preferred).

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on TikToknorth_east before you apply. If we got something wrong, report this listing.