AI Jailbreak & Prompt-Injection Security Expert

In short

micro1 is looking for AI security experts to test how AI models can be tricked into unsafe answers, then help make them safer. You do not need prior AI experience, because your knowledge of security and testing is what counts. It may suit you if you already know how to find weaknesses in systems and explain them clearly.

What you will do

• Design and run tests that try to get AI models to break their safety rules, including ethical jailbreaks and prompt injection.
• Explore complex, multi-step attacks that can slip past a model's defenses.
• Build and update test suites that check again and again for the same weak spots.
• Turn your findings into clear reports and presentations for technical and non-technical readers.
• Work with technical teammates to suggest fixes that reduce risk.

What you need to apply

• At least 2 years of experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security field.
• Proven experience finding weaknesses such as jailbreaks, prompt injection, or tool-use abuse.
• Strong written and spoken English for documentation and teamwork.
• Familiarity with current LLM architectures, prompt engineering, and security assessment tools is a strong plus.

Who can apply

The role is open to people from anywhere in the world, since no country restriction is stated. It is a remote freelance contract with a minimum of 2 years of experience, and there are 20 openings.