AI Safety Expert - Red Team

Mercor; San Francisco (CA); Remote; USD 66,000 - 85,000; Full time

Job summary

Mercor connects elite AI researchers with leading labs and offers remote contract roles in AI safety. The AI Safety Experts will red team conversational models to uncover jailbreaks, prompt injections, and misuse cases while documenting findings.

The role requires fluency in English and Swedish and prior adversarial experience, with strong ability to communicate risk to mixed audiences. Applicants will annotate failures, classify vulnerabilities, and develop reproducible reports and attack

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

Fluent English

Fluent Swedish

Red team experience

Cybersecurity

Strong communication

Job description

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.

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome


• For any help or support, reach out to: [e-mail]