Mercor partners with leading AI labs and enterprises to train frontier models using human expertise. You will collaborate with top researchers and contribute to improving next-generation AI systems in your domain.
Mercor is seeking individuals interested in cybersecurity to contribute to AI safety initiatives through red teaming activities.
In this role, you will help test and improve the robustness of large language models (LLMs) by exploring how they respond to adversarial prompts and edge cases.
Advertisement
This opportunity is ideal for motivated individuals without formal cybersecurity experience who are comfortable working with AI systems and eager to contribute to improving their safety and reliability.
Advertisement
You will be redirected to the company's website to complete your application.
Explore other opportunities in related specializations:
Software Engineer (Python, JavaScript/TypeScript, Go)
SecOps Engineer
Python + Go Developer
TypeScript + Rust Developer
Discover more opportunities that match your skills and interests.