AI Safety Expert - Red Team

mercor; United States; Remote; USD 66,000 - 85,000; Full time

Job summary

Mercor is hiring AI Safety Experts to remotely assess and harden AI systems. You will lead red team exercises on English and Swedish language models, uncover jailbreaks, and document findings with actionable guidance.

The role requires strong communication to explain risks to diverse stakeholders, and you will work asynchronously to deliver high-quality attack cases and datasets for clients.

Qualifications

• Fluent in English and Swedish.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

Bilingual English/Swedish

Red team experience

Adversarial ML knowledge

Cybersecurity awareness

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .

Position: AI Safety Experts — English & Swedish

Type: Contract

Compensation: $48–$62/hour

Location: Remote

Role Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance .

Qualifications

Must-Have

• Fluent in English and Swedish .
• Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing.
• Strong communication skills to explain risks to technical and non-technical stakeholders.

Preferred

• Experience with Adversarial ML , Cybersecurity , and Socio-technical risk .
• Skills in Creative probing such as psychology, acting, or unconventional adversarial thinking.