Product Manager, Red Team Platform & AI Security

TikTok; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

TikTok is seeking a seasoned Security Engineer to lead adversarial testing across global content safety systems. You will design threat-discovery programs, build scalable sample pipelines, and drive red-team learnings into policy and product improvements.

Join a cross-functional team in Singapore and shape defenses against evasion techniques while developing AI agent tooling to automate assessments. This role requires deep expertise in content security and program leadership.

Qualifications

• Bachelor's degree or above in Computer Science, Information Security, or related fields.
• 5+ years of experience in content security, trust & safety, or adversarial testing.
• Hands-on experience with AI/LLM applications: agent workflows, prompt engineering, or automation tools.
• Proven ability to manage complex, multi-workstream programs with cross-functional dependencies.

Responsibilities

• Threat Discovery & Risk Analysis: identify emerging abuse patterns and translate signals into actionable threat pattern cards.
• Attack Sample Construction: define methodologies, tooling, and quality standards for scalable adversarial samples.
• Adversarial Evaluation & Remediation: run evaluation programs and drive improvements from findings.
• AI Agent Development: lead design and deployment of LLM-powered agents to automate red team operations.

Skills

Content security

Trust & safety

Adversarial testing

AI/LLM applications

Program management

Education

Bachelor's degree or above in Computer Science, Information Security, or related fields

Job description

TikTok is seeking a seasoned Security Engineer to lead adversarial testing across global content safety systems. You will design threat-discovery programs, build scalable sample pipelines, and drive red-team learnings into policy and product improvements.

Join a cross-functional team in Singapore and shape defenses against evasion techniques while developing AI agent tooling to automate assessments. This role requires deep expertise in content security and program leadership.