OpenAI08.04.2026
Researcher, Safety & Privacy
Зарплата не указана
Полная занятостьSan Francisco
Обязанности
- 01Help define and operationalize frameworks for identifying and addressing frontier risks (e.g., bioweapon instructions, malware creation, suicide/self-harm risks, jailbreaks) while ensuring privacy guarantees remain intact
- 02Design and implement privacy-first architectures for detecting and mitigating harmful model behaviors
- 03Build frameworks for auditable private identification of high-risk content (jailbreaks, cyber threats, or weaponization instructions)
- 04Develop strict, auditable mechanisms triggered only by harm signals
- 05Drive the development of automated safety systems that preserve privacy at every level
Требования
- 01Are a researcher with deep interest in privacy, security, and AI safety, motivated by building systems that are both trustworthy and effective at scale
- 02Hold a PhD or equivalent experience in Computer Science, Cryptography, Security, Machine Learning, or related fields
- 03Have the ability to translate ambiguous problem spaces into formal frameworks and deployable systems
- 04Demonstrate proficiency in privacy-preserving computation (e.g., secure enclaves, MPC, differential privacy)
- 05Demonstrate proficiency in security and adversarial systems
- 06Demonstrate proficiency in machine learning safety or alignment
- 07Have experience designing robust systems under adversarial threat models
- 08Have experience with AI safety, jailbreak detection, or model alignment
- 09Are familiar with privacy-preserving machine learning techniques, algorithmic auditing and/or secure system design
Условия
- 01Background checks administered in accordance with applicable law
- 02Equal opportunity employer, no discrimination based on protected characteristics
- 03Commitment to providing reasonable accommodations for applicants with disabilities
- 04OpenAI Global Applicant Privacy Policy applies