AI Safety Red Teamer (Remote) - English & Bengali

mercor; United Kingdom; Remote; GBP 21,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts fluent in English and Bengali for remote contract work. You will red team AI models, identify jailbreaks and misuse cases, and generate high-quality data with clear risk annotations. Strong communication of risks to diverse stakeholders is essential.

Preferred candidates have AI adversarial testing or cybersecurity experience and can work across sensitive topics with established guidelines.

Qualifications

• Fluent in English and Bengali required.
• Experience in AI adversarial testing or cybersecurity is preferred.
• Ability to clearly communicate risks to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents focusing on jailbreaks, prompt injections, misuse, and bias.
• Create and annotate high-quality data; classify vulnerabilities and report systemic risks.
• Apply taxonomies, benchmarks, and playbooks to ensure consistent testing results.
• Document reproducibly and produce reports, datasets, and attack cases for customers.
• Review AI outputs on sensitive topics like bias and misinformation; work under guidelines.

Skills

English

Bengali

Red Teaming

Risk Communication

Job description

Mercor is seeking AI Safety Experts fluent in English and Bengali for remote contract work. You will red team AI models, identify jailbreaks and misuse cases, and generate high-quality data with clear risk annotations. Strong communication of risks to diverse stakeholders is essential.

Preferred candidates have AI adversarial testing or cybersecurity experience and can work across sensitive topics with established guidelines.