Frontier AI Safety Researcher

openai; General Trias; On-site; PHP 10,618,000 - 15,615,000; Full time

Job summary

OpenAI is seeking exceptional researchers to push the frontier of safety mitigations for frontier AI models. You will derisk models by developing novel safety techniques drawn from interpretability, control, and alignment, contributing to a safer future of AGI.

This role requires strong technical depth and collaboration across misalignment, cybersecurity, and biology domains to build scalable, end-to-end safety stacks and robust safety systems.

Qualifications

• 2+ years of experience in AI safety or related field.
• Ph.D. or equivalent in computer science, machine learning, or related field.
• Proficiency in Python or similar languages.
• Experience in RLHF, interpretability, robustness, alignment, or control.

Responsibilities

• Identify emerging AI safety risks and develop methodologies to mitigate them.
• Build and refine evaluations to assess risk impact with domain experts as needed.
• Set research directions to improve safety, alignment, and robustness of AI systems.
• Contribute to best practices guidelines for AI safety for OpenAI and the industry.
• Design and evaluate red-teaming pipelines to test end-to-end safety of deployed models.

Skills

Python

RLHF

Interpretability

Robustness

Control

Human-AI collaboration

Education

Ph.D. in Computer Science

Job description

OpenAI is seeking exceptional researchers to push the frontier of safety mitigations for frontier AI models. You will derisk models by developing novel safety techniques drawn from interpretability, control, and alignment, contributing to a safer future of AGI.

This role requires strong technical depth and collaboration across misalignment, cybersecurity, and biology domains to build scalable, end-to-end safety stacks and robust safety systems.