Researcher, Safety Training, National Security

at OpenAI

📍 United States
📍 Washington, United States
📍 San Francisco, United States

USD 380,000-500,000 per year

MIDDLE

✅ Remote ✅ On-site

✅ Relocation

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI @ 5 Deep Learning @ 6 Machine Learning @ 3 Reinforcement Learning Security

Details

The Safety Training research team works to advance methods for implementing safe behavior in AI models and applying these advances to make deployed models safe and beneficial. Focus areas include nuanced safety behaviors, robustness to bad actors, privacy and security risks, and trustworthy behavior in safety-critical situations.

The role focuses on training and evaluating models for U.S. government use, particularly national security applications. The researcher will advance safety post-training and robustness so models can follow nuanced policies while preserving their usefulness and capabilities.

Responsibilities

Research and implement methods for safety training, reinforcement learning, and adversarial robustness.
Develop evaluations, identify model failure modes, and use findings to improve training.
Work with research, engineering, security, and policy partners to support safe and reliable deployment.

Requirements

4+ years of relevant AI safety research experience, including RLHF, adversarial training, or robustness.
A degree in computer science, machine learning, or a related field.
Strong deep learning research or engineering skills.
Experience improving model safety for deployment.
Collaborative research skills and motivation to support the responsible use of AI in safety-critical settings.
Active TS/SCI clearance or equivalent.

Benefits

Equity, performance-related bonuses for eligible employees, and benefits including medical, dental, and vision insurance.
Health Savings Accounts, flexible spending accounts, commuter benefits, and a 401(k) retirement plan with employer match.
Paid parental, medical, caregiver, sick, and safe leave.
Flexible paid time off for exempt employees and up to 15 days annually for non-exempt employees.
Paid company holidays and office closures.
Mental health and wellness support.
Employer-paid basic life and disability coverage.
Annual learning and development stipend.
Daily meals in offices and eligible meal delivery credits.
Relocation support for eligible employees.
Additional benefits may include charitable donation matching and wellness stipends.