AI Safety Red Teamer, English and Gujarati

Help strengthen conversational AI by probing models for weaknesses, documenting risks, and producing high-quality safety data. This text-based remote role focuses on adversarial testing and review of AI outputs, including work involving sensitive subjects such as bias, misinformation, and harmful behavior. Key Responsibilities

• Test conversational AI models and agents for jailbreaks, prompt injection, misuse scenarios, bias exploitation, and multi-turn manipulation.
• Review AI outputs, annotate failures, classify vulnerabilities, and flag systemic risks.
• Use established taxonomies, benchmarks, and playbooks to conduct consistent testing.
• Create reproducible reports, datasets, and attack cases that teams can use to improve AI systems.
• Expand evaluation coverage by identifying vulnerabilities that automated testing may miss.

• Native fluency in both English and Gujarati.
• Strong judgment about whether AI responses are accurate, complete, and appropriate, with the ability to explain that assessment.
• Close attention to subtle errors, inconsistencies, and gaps.
• Ability to follow quality standards and guidelines consistently.
• Clear communication with both technical and non-technical audiences.
• Adaptability across projects, task types, and stakeholders.

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

• Remote, hourly engagement.
• Participation in higher-sensitivity projects is optional. Topics will be communicated before exposure, with clear guidelines and wellness resources available.

$16 to $22 per hour.