M- Work from
- Australia
- Contract
- Full-time
- Posted
- 9 November 2026
- Apply by
- 9 December 2026
Position: AI Safety Experts — English & SwedishType:ContractCompensation:$48–$62/hourLocation:Remote
About the role
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.
Requirements
- 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.
Nice to have
- Experience with Adversarial ML, Cybersecurity, and Socio-technical risk.
- Skills in Creative probing such as psychology, acting, or unconventional adversarial thinking.
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.
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.
How to apply
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
B
L
O
T
Discussion
No comments yet. Ask a question or share a tip about this role.