Content Evaluation QA

Our client is a leading global short-video and social media platform. Their Safety Model Operations (SMO) team is responsible for building, optimizing, and maintaining machine learning models and operational processes that support the platform's Trust & Safety systems, ensuring automated safety models perform effectively in identifying harmful content, mitigating risks, and maintaining a safe user environment across regions.

The SMO Delivery Team plays a critical role in the organization, carrying out the full spectrum of quality assurance activities for each project — including detailed reviews and complex root cause analyses (RCAs) to ensure labeling accuracy and consistency, monitoring quality performance against project-specific KPIs, identifying trends and process gaps, providing structured feedback to the Central Project Team, and supporting continual optimization of workflows, tools, and evaluation methodologies, as well as improving the performance of AI models.

RESPONSIBILITIES

• Construct and iterate the core Golden Sets for the content safety ecosystem, curating long-tail, high-risk, and complex edge cases to establish highly accurate data standards (Ground Truth) for platform safety policies, AI model evaluation, and global enforcement teams.
• Conduct deep-dive analyses on high-risk and highly debated safety cases to accurately identify misapplication patterns and risk evolution trends; lead the synthesis and abstraction of complex rules, translating macro policies into highly logical and executable Standard Operating Procedures (SOPs) and operational guidelines.
• Drive the content safety data closed-loop, collaborating cross-functionally with Operations, Algorithm, Product, and global teams to identify system vulnerabilities based on Golden Set metrics, achieving bidirectional improvements in human review quality and AI agent interception efficacy.
• Systematize universal methodologies for the content quality management framework and establish robust daily Quality Assurance (QA) mechanisms; track and attribute core data metrics to enhance overall data accuracy and operational efficiency.

REQUIREMENTS

• Proven experience in internet Trust & Safety, Quality Assurance (QA), AI data evaluation, or policy operations.
• Exceptional logical reasoning and synthesis skills, with a proven ability to navigate complex and ambiguous business scenarios to identify root causes and independently deliver structured solutions.
• Professional working proficiency in English, with extreme attention to detail and standard consistency, paired with outstanding cross-cultural written and verbal communication skills.
• Highly self-motivated with a strong sense of ownership; capable of embracing uncertainty in a fast-paced, cross-border collaborative environment, and able to effectively drive multiple parallel tasks to deliver solid business results.

LANGUAGE REQUIREMENTS

This role is open across multiple language markets, with one position per language listed below.

Japanese, Korean, English + Mandarin, Spanish, Bahasa Indonesia, Arabic, Thai, Vietnamese, French, Portuguese, German, Tagalog, Turkish, Italian

Candidates must hold at least a B2 proficiency level in the relevant language, as it is mandatory for daily liaison with the local market team and for accurate communication of business information.

PREFERRED QUALIFICATIONS

• Familiarity with machine learning logic and data labeling frameworks is a strong plus.

HOW TO APPLY

Send your updated resume to [email protected]