Job Description

About the team

The Safety Model Operations [SMO] team is responsible for building, optimizing, and maintaining machine learning models and operational processes that support TikTok's Trust & Safety systems. We ensure that 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. Its primary responsibility is to carry out the full spectrum of quality assurance activities for each project. This includes:

- Conducting detailed reviews and complex RCA's to ensure labeling accuracy and consistency

- Monitoring quality performance and compliance against project-specific KPIs

- Identifying trends, risks, and potential gaps in processes or guidelines

- Providing structured feedback and improvement recommendations to the Central Project Team

- Supporting continual optimization of workflows, tools, and evaluation methodologies

- Improve Model performance of AI models

What will I do?

As the Content Quality & Evaluation Team Lead, you will lead a team of Content Quality and Evaluation Specialist to build the Golden Sets that define Ground Truth for platform policies, AI model evaluation, and global enforcement teams. You will drive deep-dive analyses on high-risk and contentious safety cases, transforming macro policies into crystal-clear SOPs and operational guidelines. By orchestrating a continuous closed-loop feedback system across Operations, Algorithm, Product, and global teams, you will turn Golden Set insights into system-wide improvements—enhancing both human review quality and AI interception accuracy. You will also systematize quality methodologies, establish robust QA mechanisms, and own core data metrics.

Responsibilities

1. Lead Golden Set Production: Lead the team to produce high-quality datasets (Golden Sets) for model training and evaluation, curating long-tail, high-risk, and complex edge cases to establish accurate Ground Truth for policies, AI models, and global enforcement teams.

2. Drive Deep-Dive & Process Abstraction: Oversee deep-dive analyses on high-risk and highly debated safety cases to identify misapplication patterns and risk trends, translating macro policies into logical SOPs and operational guidelines.

3. Manage Quality Performance: Comprehensively manage quality performance across multiple workflows, drive continuous improvement, and ensure the achievement of both efficiency and quality goals.

4. Lead Cross-Functional Collaboration: Lead collaboration 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.

5. Systematize QA Methodologies: Systematize universal methodologies for the content quality management framework and establish robust daily QA mechanisms, tracking core data metrics to enhance accuracy and operational efficiency.

6. Proactively Identify & Mitigate Risks: Proactively identify quality risks and assess their impact on workflows, agilely resolving risks while ensuring stable delivery.

7. Build Team Capability: Drive team capability building and operational management, including personnel development and resource allocation, to ensure