Search
Go
Researcher, Safety Training, National Security
Summary by AIEngineer.careers
Researcher, Safety Training, National Security is a AI Safety Engineer role (full-time). with OpenAI. in SAN FRANCISCO, US. Compensation shown: $380K–$500K. Imported listing (source: emploive.com). Apply on the employer's site (emploive.com).
Imported listing (source: emploive.com) · Apply on emploive.com
SAN FRANCISCO · US
$380K–$500K
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from emploive.com
OpenAI is seeking a Researcher for Safety Training with a focus on national security applications. The role involves advancing safety post-training and robustness to ensure AI models follow nuanced policies while remaining useful and safe for U.S. government use. Candidates must have active TS/SCI clearance or equivalent.
Responsibilities
- Research and implement methods for safety training, reinforcement learning, and adversarial robustness.
- Develop evaluations to identify model failure modes and improve training processes.
- Collaborate with research, engineering, security, and policy partners to support safe deployment.
Requirements
- 4+ years of relevant AI safety research experience, including RLHF, adversarial training, or robustness.
- Degree in computer science, machine learning, or related field.
- Strong deep learning research or engineering skills.
- Active TS/SCI clearance or equivalent.
Nice to Have
- Experience improving model safety for deployment.
- Motivation by OpenAI’s mission and responsible use of AI in safety-critical settings.
OpenAI
San Francisco · US · 7850+ employees
OpenAI is an AI research and deployment company that develops large-scale artificial intelligence models and safety systems. It focuses on advancing artificial general intelligence through research, product development, and collaborative partnerships.
