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

Mercor; Greater London; À distance; GBP 50 000 - 65 000; Temps partiel

Résumé du poste

Mercor is seeking AI Safety Experts — English & Danish for a remote contract role. You will red team conversational AI models and simulate misuse to improve safety and reliability.

You will generate high-quality data, document findings, and work with clients across projects, asynchronously and independently.

Fluency in English and Danish and prior adversarial experience are essential for success.

Qualifications

• Fluent in English and Danish, written and spoken.
• Experience in AI adversarial red teaming or cybersecurity.
• Strong ability to explain risks to technical and non-technical stakeholders.
• Ability to move across multiple projects and customers.

Responsabilités

• 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 maintain 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.

Connaissances

Fluent in English & Danish

Red teaming in AI adversarial work

Clear technical communication

Cross-project adaptability

Description du poste

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 & Danish

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 maintain 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 & Danish.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.
• Ability to thrive on moving across projects and customers.

Preferred

• Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Cybersecurity skills: penetration testing, exploit development, reverse engineering.
• Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.