Related skills
security machine learning differential privacy mpc secure enclaves📋 Description
- Design privacy-first architectures to detect and mitigate harmful model behaviors.
- Build auditable private detection of high-risk content (jailbreaks, weaponization).
- Develop strict, auditable harm-signal triggered mechanisms.
- Drive automated safety systems that preserve privacy at all levels.
🎯 Requirements
- PhD or equivalent in CS, cryptography, security, ML, or related fields.
- Deep interest in privacy, security, and AI safety; scalable trustworthy systems.
- Translate ambiguous problems into formal frameworks and deployable systems.
- Proficiency in privacy-preserving computation, ML safety, or security.
- Experience with AI safety, jailbreak detection, or model alignment.
- Familiar with privacy-preserving ML techniques, algorithmic auditing.
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!