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

mercor; Finland; Remote; EUR 59,000 - 76,000; Full time

Job summary

Mercor is seeking AI Safety Experts to remotely assess and test AI systems, focusing on English and Finnish. The role involves red teaming, vulnerability annotation, and documenting findings to help clients act on risks.

Candidates should have strong English and Finnish, plus background in cybersecurity or socio-technical risk. Remote work enables asynchronous collaboration with global labs and teams.

Qualifications

• Must be fluent in English and Finnish.
• Experience in red teaming, AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to communicate risks clearly to both technical and non-technical stakeholders.
• Preferred: Adversarial ML, jailbreak datasets, prompt injection, model extraction.
• Preferred: Cybersecurity background such as penetration testing and exploit development.

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 structured approaches using taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document findings 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

Red teaming

AI adversarial work

Cybersecurity

Socio-technical probing

Communication

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 & Finnish

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 structured approaches using taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document findings 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 and Finnish.
• Must-Have Prior experience in red teaming, AI adversarial work , cybersecurity , or socio-technical probing.
• Must-Have Ability to communicate risks clearly to both technical and non-technical stakeholders.
• Preferred Experience with Adversarial ML , including jailbreak datasets, prompt injection, and model extraction.
• Preferred Background in Cybersecurity , such as penetration testing and exploit development.
• Preferred Expertise in socio-technical risk, including harassment/disinfo probing and abuse analysis.