AI Safety Red Teamer, Remote — English & Bengali

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

Job summary

Mercor is seeking AI Safety Experts to remotely test and critique conversational AI systems, focusing on jailbreaks, bias, and risk exposure. You will generate high-quality human data, annotate issues, and draft reproducible reports for customers.

Ideal candidates have experience in AI adversarial work or cybersecurity and can clearly communicate risk to diverse stakeholders. This is a remote, contract role with competitive hourly compensation.

Qualifications

• Fluent in English and Bengali.
• Prior red teaming in AI adversarial work or cybersecurity.
• Ability to communicate risks clearly to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents, focusing on jailbreaks and prompt injections.
• Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks for testing.
• Document reproducibly with reports, datasets, and attack cases.
• Review AI outputs on sensitive topics; participate in higher-sensitivity projects as guided.

Skills

English

Bengali

Red team experience

AI adversarial work

Cybersecurity

Stakeholder communication

Tools

Adversarial ML

Cybersecurity

Job description

Mercor is seeking AI Safety Experts to remotely test and critique conversational AI systems, focusing on jailbreaks, bias, and risk exposure. You will generate high-quality human data, annotate issues, and draft reproducible reports for customers.

Ideal candidates have experience in AI adversarial work or cybersecurity and can clearly communicate risk to diverse stakeholders. This is a remote, contract role with competitive hourly compensation.