GenAI Adversarial Testing & Safety Analyst

Bytedance; Singapore; On-site; SGD 70,000 - 100,000; Full time

Job summary

ByteDance's Trust & Safety GenAI & Emerging Product team seeks an experienced adversarial tester to strengthen the safety and risk management of our AI products in Singapore. You will conduct structured testing, explore model behavior across contexts, and document findings with clear risk assessments and mitigation recommendations.

You will collaborate with policy, product, and engineering teams to validate mitigations and drive improvements in safeguards before and after launch.

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 ways AI systems can be compromised under adversarial conditions
• Ability to investigate ambiguous problems, identify non-obvious failure modes and abuse patterns, and produce clear, evidence-based conclusions
• Strong communication skills
• Ability to manage multiple priorities and collaborate with cross-functional teams

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 relevant to content safety
• Document findings clearly and consistently, including risk descriptions, reproduction steps, severity assessments, and mitigation recommendations
• 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 shifts in the external risk landscape

Skills

Structured adversarial testing

Prompt testing

LLM evaluation

AI safety risk awareness

Independent investigation

Clear communication

Cross-functional collaboration

Job description

ByteDance's Trust & Safety GenAI & Emerging Product team seeks an experienced adversarial tester to strengthen the safety and risk management of our AI products in Singapore. You will conduct structured testing, explore model behavior across contexts, and document findings with clear risk assessments and mitigation recommendations.

You will collaborate with policy, product, and engineering teams to validate mitigations and drive improvements in safeguards before and after launch.