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

๐Ÿข mercor ยท all mercor jobs
๐Ÿ“ Ireland
๐Ÿ’ฐ USD 48 - 62 / hourly
๐Ÿ“… Posted 2026-08-23 ยท via Himalayas
๐Ÿท AI-Safety,AI-Red-Teaming,Cybersecurity,Adversarial-Machine-Learning,AI-ML-Testing,AI-Safety-Specialist,AI-Safety-Analyst,AI-Safety-Practitioner,AI-Safety-Expert,AI-Safety-Researcher,AI-Security-Specialist,Safety-AI,Safety-AI-Engineering,Remote-AI-Specialist
Apply on original site โ†—

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 โ€” English & Danish
Type: Contract
Compensation: $48โ€“$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.

Application Process (Takes 20โ€“30 mins to complete)

- Upload resume

- AI interview based on your resume

- Submit form

Resources & Support

- For details about the interview process and platform information, please check:

- For any help or support, reach out to:

PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.

Originally posted on Himalayas

โ† All remote jobs