Remote AI Safety Red Team Expert

SaidGig; New York (NY); Remote; USD 23,000 - 34,000; Part time

Job summary

SaidGig is seeking a text-based, remote, hourly role to strengthen conversational AI systems. You will probe models with adversarial inputs, identify vulnerabilities, and build high-quality safety datasets, reports, and attack cases.

Responsibilities include red-teaming AI models, reviewing outputs on bias and safety, annotating failures, and documenting reproducible results to guide improvements. This role emphasizes structured risk assessment and clear communication across client contexts.

Qualifications

• Native fluency in English and Vietnamese.
• Experience in AI adversarial red teaming.
• Ability to communicate risks to technical and non-technical audiences.

Responsibilities

• Red team conversational AI models using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Review AI outputs involving sensitive topics, including bias, misinformation, and harmful behaviors.
• Annotate model failures, classify vulnerabilities, and flag systemic risks.
• Use established taxonomies, benchmarks, and playbooks to conduct consistent testing.
• Create reproducible documentation and artifacts that support improvements to AI systems.

Skills

Bilingual: English & Vietnamese

Red teaming experience

Structured risk communication

Job description

SaidGig is seeking a text-based, remote, hourly role to strengthen conversational AI systems. You will probe models with adversarial inputs, identify vulnerabilities, and build high-quality safety datasets, reports, and attack cases.

Responsibilities include red-teaming AI models, reviewing outputs on bias and safety, annotating failures, and documenting reproducible results to guide improvements. This role emphasizes structured risk assessment and clear communication across client contexts.