AI Content Red Team Analyst - Trust and Safety Global Operations Singapore Regular

ByteDance; Singapore; Sur place; SGD 70 000 - 100 000; Plein temps

Résumé du poste

ByteDance is looking for an AI Content Red Team Analyst for their Trust and Safety team in Singapore. This role involves conducting adversarial testing on generative AI models to ensure optimal safety and risk management. The ideal candidate has over 3 years of experience in Trust & Safety or cybersecurity, with a strong interest in AI safety risks and effective communication skills.

The candidate will work cross-functionally to document findings, recommend mitigations, and partner with teams to improve safety before and after product launches. A comprehensive support program for wellbeing is provided to all employees.

Qualifications

• 3+ years in Trust & Safety, cybersecurity, or related fields.
• Experience with prompt testing and adversarial QA.
• Familiarity with AI safety risks.

Responsabilités

• Conduct adversarial testing on AI models to identify vulnerabilities.
• Document findings and provide mitigation recommendations.
• Stay updated on emerging adversarial trends.

Connaissances

Trust & Safety

Cybersecurity

Risk/Adversarial Testing

Strong Communication Skills

Problem Investigation

AI Safety Risks

Description du poste

AI Content Red Team Analyst - Trust and Safety

Location:

Team: Global Operations

Employment Type: Regular

Job Code: A222833A

Responsibilities

The Trust & Safety GenAI & Emerging Product team empowers the development of generative AI models and applications by building a world‑class safety, testing, and risk management system.

The AI Content Red Team focuses on unstructured adversarial testing of ByteDance’s generative AI products and models to uncover emerging risks, in addition to structured evaluations. The role requires attacker‑minded testing, risk discovery, and clear operational feedback loops to inform product decisions, policy development, mitigations, and long‑term evaluation strategy. The responsibilities include probing models and product experiences across modalities, use cases, and abuse patterns to identify failure modes, stress‑test safeguards, and help teams improve safety before and after launch.

• 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 that may not be captured in standard evaluations.
• 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 (policy, product, business teams) to ensure mitigation validation and root cause closure.
• Support development of testing playbooks, taxonomies, and internal knowledge bases.
• Stay updated on emerging adversarial trends (e.g., deepfakes, multimodal manipulation, coordinated abuse) and shifts in the external risk landscape.

Qualifications

Minimum Qualification(s)

• 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 the ways AI systems can be compromised under adversarial conditions.
• Demonstrated ability to independently 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 effectively with cross‑functional teams.

Preferred Qualification(s)

• Experience working with agentic AI tools to scale your impact, including building/operating AI tools to make processes efficient and effective.

Potential Hazards

Content that this role interacts with may include images, video, and text related to everyday life, but it can also include bullying, hate speech, child safety, depictions of self‑harm or harm to others and animals. Consequently, the role may be exposed to harmful content on a daily basis. We provide comprehensive programs to support physical and mental wellbeing throughout each employee’s journey with us.