AI Red Team Engineer
You will conduct adversarial testing and turn reproducible failures into practical safety improvements.
About the role
The work includes threat modeling, manual and automated testing, attack-scenario design, clear reporting, and verification of mitigations.
What you'll do
- Develop adversarial test plans for new and existing product capabilities.
- Test realistic misuse scenarios, prompt injection, and attempts to bypass safety controls.
- Develop repeatable methods and automation for confirmed failure modes.
- Work with engineering, product, research, and policy partners to verify corrective changes.
What we're looking for
- Experience in red teaming, penetration testing, application security, or adversarial machine learning.
- Experience finding novel attack paths and reducing them to reliable reproduction steps.
- Enough scripting ability to turn manual discoveries into repeatable tests.
- Clear writing and the ability to explain technical risk to several disciplines.
Preferred experience
- Public security research, responsible disclosures, or other relevant technical work.
Equal opportunity
Entlegnant, the company behind Leiolai, is an equal opportunity employer. We consider qualified applicants without regard to race, color, religion, sex, gender identity or expression, sexual orientation, national origin, ancestry, age, disability, veteran status, genetic information, or any other status protected by law.
Applicants must be at least 18. If you need an accommodation during the application process, email talent@leiolai.com.
Apply
Submit your resume and a few details below. A cover letter is optional.