GenAI Content Red Team - Adversarial Safety & Risk

ByteDance; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

ByteDance's Trust & Safety GenAI & Emerging Product team seeks a skilled analyst to conduct structured adversarial testing of AI models, policies, and features across modalities. You will probe jailbreaks, prompt-based attacks, and abuse patterns to uncover risks and inform mitigations before and after launch.

Collaborate with policy, product, data science, and ops teams across markets. Strong judgment, analytical rigor, and clear reporting are essential as you translate findings into actionable

Qualifications

• 3+ years in Trust & Safety, cybersecurity, risk/adversarial testing, or related fields
• Experience with prompt testing, jailbreak analysis, LLM evaluation, or adversarial QA
• Familiarity with AI safety risks (jailbreaks, hallucinations, bias, misuse patterns)
• Strong interest in GenAI safety and ability to identify failure modes and abuse patterns
• Demonstrated ability to investigate ambiguous problems and produce evidence-based conclusions
• Strong communication skills

Responsibilities

• Conduct structured adversarial testing on AI models, features, and policies to identify vulnerabilities and emerging risks
• Explore product behavior across contexts and user journeys to identify model failure modes
• Investigate jailbreaks, evasions, prompt-based attacks, and other adversarial techniques
• Document findings clearly with risk descriptions, reproduction steps, severity, and mitigations
• Partner with cross functional stakeholders to ensure mitigation validation and root cause closure
• Support development of testing playbooks, taxonomies, and internal knowledge bases
• Stay updated on emerging adversarial trends and external risk landscape

Skills

Trust & Safety

Cybersecurity

Adversarial testing

Prompt testing

LLM evaluation

Communication skills

Job description

ByteDance's Trust & Safety GenAI & Emerging Product team seeks a skilled analyst to conduct structured adversarial testing of AI models, policies, and features across modalities. You will probe jailbreaks, prompt-based attacks, and abuse patterns to uncover risks and inform mitigations before and after launch.

Collaborate with policy, product, data science, and ops teams across markets. Strong judgment, analytical rigor, and clear reporting are essential as you translate findings into actionable