Model Safety Engineer

About the role

The work includes threat models, representative evaluations, model development, adversarial testing, production monitoring, and measured mitigation work.

What you'll do

• Develop models and evaluations that detect misuse and anomalous behavior.
• Create representative data and tests for known and emerging safety risks.
• Conduct adversarial testing and use the results to improve mitigations.
• Take promising research from experiment through production evaluation and monitoring.

What we're looking for

• Experience in machine learning engineering, research engineering, or applied research.
• Strong Python skills and experience developing production machine learning systems.
• Experience with classifiers, anomaly detection, adversarial testing, or behavioral machine learning.
• The ability to explain technical safety work to non-technical partners.

Preferred experience

• Experience moving safety research into a production product.

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.