AI Safety Red Team Expert, English & Danish

SaidGig; New York (NY); Remote; USD 66.000 - 85.000; Teilzeit

Zusammenfassung

SaidGig is seeking a remote hourly contractor to strengthen conversational AI by adversarial testing across English and Danish, focusing on text-based red teaming.

You will test jailbreaks, prompt injections, misuse cases, and bias exploitation; annotate failures; create reproducible reports and safety datasets to help teams improve robustness and trust in AI systems.

Qualifikationen

• Native or near-native fluency in English and Danish.
• Experience conducting adversarial AI testing or cybersecurity.
• Ability to use testing frameworks and benchmarks to assess models.

Aufgaben

• Test conversational AI models for jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Review AI outputs on bias, misinformation, and harmful behavior.
• Annotate failures, classify vulnerabilities, and flag systemic risks.

Kenntnisse

Bilingual English/Danish

Red teaming experience

Frameworks and benchmarks

Clear communication

Adaptability across projects

Jobbeschreibung

Help strengthen conversational AI systems by probing them with adversarial inputs, identifying vulnerabilities, and producing practical safety data.

This remote role focuses on text-based AI red teaming in both English and Danish.

Key Responsibilities

• Test conversational AI models and agents for jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
• Review AI outputs involving sensitive topics, including bias, misinformation, and harmful behaviors
• Annotate failures, classify vulnerabilities, flag systemic risks, and create high-quality human data
• Use established taxonomies, benchmarks, and playbooks to apply testing consistently
• Create reproducible reports, datasets, and attack cases that teams can use to improve AI systems

Qualifications

• Native fluency in both English and Danish is required
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
• Ability to use frameworks and benchmarks to test systems methodically
• Clear communication skills for explaining risks to technical and non-technical audiences
• Comfort adapting across projects and customer contexts

Preferred Experience

• Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, or model extraction
• Cybersecurity, including penetration testing, exploit development, or reverse engineering
• Socio-technical risk testing, including harassment or misinformation probing, abuse analysis, or conversational AI testing
• Psychology, acting, or writing skills that support unconventional adversarial thinking

Work Terms

• Remote, hourly engagement.
• All work is text-based.
• Higher-sensitivity projects are optional. Topics are communicated before exposure, with clear guidelines and wellness resources available.

Compensation

• $48 to $62 per hour.

Impact

• Identify vulnerabilities that automated testing may miss.
• Expand evaluation coverage across more scenarios and help reduce unexpected production behavior.
• Deliver reproducible safety artifacts that help make AI systems more robust, safe, and trustworthy.