# Researcher, Safety & Privacy

**Company:** [OpenAI](https://hotfix.jobs/companies/openai)
**Location:** San Francisco, CA
**Role:** Other
**Salary:** $295k – $445k/yr
**Skills:** Differential Privacy, Secure Enclaves, Mpc, Machine Learning Safety, Ai Alignment, Jailbreak Detection, Privacy-Preserving Ml, Algorithmic Auditing, Adversarial Threat Models, Cryptography
**Posted:** 2026-04-07

> Designs privacy-preserving safety systems for frontier AI models, focusing on auditable harm detection (jailbreaks, cyber threats, bioweapons) without exposing user data. Requires PhD in CS/crypto/ML/security and expertise in privacy tech like MPC and differential privacy.

## Job Description

## Responsibilities
- Design and implement privacy-first architectures for detecting and mitigating harmful model behaviors.
- Build frameworks for auditable private identification of high-risk content (jailbreaks, cyber threats, or weaponization instructions).
- Develop strict, auditable mechanisms triggered only by harm signals.
- Drive the development of automated safety systems that preserve privacy at every level.

## Requirements
- Deep interest in privacy, security, and AI safety, motivated by building systems that are both trustworthy and effective at scale.
- PhD or equivalent experience in Computer Science, Cryptography, Security, Machine Learning, or related fields.
- Ability to translate ambiguous problem spaces into formal frameworks and deployable systems.
- Proficiency in one or more of:
  - **Privacy-preserving computation** (e.g., secure enclaves, MPC, differential privacy)
  - Security and adversarial systems
  - Machine learning safety or alignment
- Experience designing robust systems under adversarial threat models.
- Experience with AI safety, jailbreak detection, or model alignment.
- Familiarity with privacy-preserving machine learning techniques, algorithmic auditing and/or secure system design.

## Similar roles

- [Safeguards Enforcement Analyst, Access Controls & Identity](https://hotfix.jobs/jobs/60c21486-9f75-456f-b022-4dbfd17c96c7) - Anthropic - San Francisco, CA - $285k – $330k/yr
- [Safeguards Enforcement Analyst, Cyber Harm](https://hotfix.jobs/jobs/564e83f4-cb18-4b7d-a214-a3013eae2b23) - Anthropic - San Francisco, CA - $285k – $330k/yr
- [Safeguards Enforcement Analyst, Integrity & Authenticity](https://hotfix.jobs/jobs/c273494b-2c98-4928-88dc-14ec308dd37e) - Anthropic - San Francisco, CA - $285k – $330k/yr
- [Legal Engineer](https://hotfix.jobs/jobs/e74b3a20-9287-4a57-8ef1-bff4d4fd6ed4) - Harvey - New York, NY - $270k – $320k/yr
- [Optical Network Engineer](https://hotfix.jobs/jobs/40fdc08a-3b64-4369-b333-b9feeb743349) - OpenAI - San Francisco, CA - $342k – $445k/yr

**Apply:** https://hotfix.jobs/jobs/17d76cba-3cf1-4ee2-8350-b95125286435
**Canonical:** https://hotfix.jobs/jobs/17d76cba-3cf1-4ee2-8350-b95125286435