Similar Jobs
See allAI Safety Expert — English & Norwegian
Jobgether
Canada
Cybersecurity
Penetration Testing
Norwegian
Adversarial Machine Learning Engineer - Red Teaming
Not Specified
Canada
Python
PyTorch
TensorFlow
STEM PhDs and Technical Domain Experts
Jobgether
Canada
AI
Research
Analytical
AI Security Engineer
Check Point
US
Penetration Testing
Web Application Security
LLM Security
AI Response Labeler / Annotator
Jobgether
US
English
Analytical Skills
Attention To Detail
Accountabilities:
- Conduct red-team evaluations of conversational AI models to identify vulnerabilities.
- Develop creative adversarial prompts to systematically probe model behavior.
- Generate high-quality human evaluation data by annotating failures.
Requirements:
- Fluent proficiency in English and Swedish.
- Prior experience in AI red teaming, adversarial AI research, or cybersecurity.
- Strong analytical and critical-thinking skills.
Benefits:
- Competitive contract compensation of $48–$62 per hour.
- Fully remote work environment with flexible asynchronous structure.
- Opportunity to contribute directly to AI safety and responsible development.
Partner Company
The partner company is a technology organization focused on AI safety and responsible AI development. They work with a remote, asynchronous team to improve the robustness of conversational AI systems.