AI Adversarial Specialist - Fully Remote | Upto $62/hr

mercor; San Francisco (CA); Remote; CAD 92,000 - 119,000; Part time

Job summary

Mercor is seeking an AI Safety Expert to remotely assess and fortify AI systems. You will red-team conversational models, identify jailbreaks and biases, and generate actionable data to help customers mitigate risks. Strong English and Swedish communication is essential, with prior adversarial or cybersecurity experience preferred.

The contract role offers remote work with flexible collaboration across time zones and teams, contributing to safer AI deployments for leading labs and researchers.

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.

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

Swedish

Red teaming

Cybersecurity

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 Details

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

• Adversarial ML, Cybersecurity, and Socio-technical risk.

Skills

• Creative probing such as psychology, acting, or unconventional adversarial thinking.