We are seeking a Researcher in Privacy-Preserving Safety to help design and build the next generation of privacy-preserving safety systems for frontier AI models. This role sits at the intersection of AI safety, security, and privacy, with a focus on developing auditable, privacy-first mechanisms that enable robust harm detection and mitigation without exposing sensitive user data.
\nYou will help define and operationalize frameworks for identifying and addressing frontier risks (e.g., bioweapon instructions, malware creation, suicide/self-harm risks, jailbreaks), while ensuring that privacy guarantees remain intact,even under adversarial conditions.
\nThis role is central to our long-term goal of scaling our automated privacy-preserving safety systems to mitigate potential harms while minimizing human review.
\nYou’ll work on foundational problems such as privacy-preserving monitoring, algorithmic auditing, secure enclaves, and adversarially robust safety enforcement protocols, helping ensure that safety systems scale without compromising user trust.
\nDesign and implement privacy-first architectures for detecting and mitigating harmful model behaviors.
\nBuild frameworks for auditable private identification of high-risk content (jailbreaks, cyber threats, or weaponization instructions).
\nDevelop strict, auditable mechanisms triggered only by harm signals.
\nDrive the development of automated safety systems that preserve privacy at every level.
\nYou might thrive in this role if you:
\nAre a researcher with deep interest in privacy, security, and AI safety, motivated by building systems that are both trustworthy and effective at scale.
\nHold a PhD or equivalent experience in Computer Science, Cryptography, Security, Machine Learning, or related fields
\nHave the ability to translate ambiguous problem spaces into formal frameworks and deployable systems
\nDemonstrate proficiency in one or more of:
\nPrivacy-preserving computation (e.g., secure enclaves, MPC, differential privacy)
\nSecurity and adversarial systems
\nMachine learning safety or alignment
\nExperience designing robust systems under adversarial threat models
\nHave experience with AI safety, jailbreak detection, or model alignment
\nAre familiar with privacy-preserving machine learning techniques, algorithmic auditing and/or secure system design
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_8385c7dc-bad","directApply":true,"hiringOrganization":{"@type":"Organization","name":"OpenAI","sameAs":"https://openai.com","logo":"https://logos.yubhub.co/openai.com.png"},"x-apply-url":"https://jobs.ashbyhq.com/openai/a0feb59d-e66b-4cc7-a685-7f9393d80fb6","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"Full time","x-salary-range":"$295K – $445K","x-skills-required":["Privacy-preserving computation","Security and adversarial systems","Machine learning safety or alignment","Experience designing robust systems under adversarial threat models","AI safety, jailbreak detection, or model alignment"],"x-skills-preferred":["Privacy-preserving machine learning techniques","Algorithmic auditing and/or secure system design"],"datePosted":"2026-04-24T12:22:44.516Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Privacy-preserving computation, Security and adversarial systems, Machine learning safety or alignment, Experience designing robust systems under adversarial threat models, AI safety, jailbreak detection, or model alignment, Privacy-preserving machine learning techniques, Algorithmic auditing and/or secure system design","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":295000,"maxValue":445000,"unitText":"YEAR"}}}]}