AI Safety Red Team Specialist (English & Punjabi) Remote

mercor; San Francisco (CA); Hybrid; GBP 21,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts (English & Punjabi) for a remote contract. You will red-team AI systems, craft adversarial scenarios, and generate actionable data to reveal vulnerabilities and risks for clients in AI research environments.

Applicants should have strong communication skills and a track record in AI adversarial work, cybersecurity, or socio-technical probing, with ability to adapt across projects and customers.

Qualifications

• Fluent in English and Punjabi.
• Experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
• Strong communication skills; can explain risks to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases for customer action.

Skills

English

Punjabi

Job description

Mercor is seeking AI Safety Experts (English & Punjabi) for a remote contract. You will red-team AI systems, craft adversarial scenarios, and generate actionable data to reveal vulnerabilities and risks for clients in AI research environments.

Applicants should have strong communication skills and a track record in AI adversarial work, cybersecurity, or socio-technical probing, with ability to adapt across projects and customers.