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

mercor; San Francisco (CA); Hybrid; GBP 50,000 - 65,000; Full time

Job summary

Mercor is seeking AI Safety Experts to red team conversational AI models and identify jailbreaks, prompt injections, and misuse cases. This remote contract role supports rapid testing across English and Dutch contexts.

You will generate high-quality human data, document reproducibly, and produce attack cases and reports that customers can act on. The position requires fluency in English and Dutch, prior adversarial testing experience, and the ability to explain risks to both technical and

Qualifications

• Fluent in English & Dutch.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• 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 to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English

Dutch

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 & Dutch. Type: Contract. Compensation: $48–$62/hour. Location: Remote.

Role Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• 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 to produce 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 & Dutch.
• Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing.
• Ability to explain risks clearly 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.

Originally posted on Himalayas