Frontier AI Safety Researcher

Triwill Group; San Francisco (CA); On-site; USD 180,000 - 320,000; Full time

Job summary

OpenAI in San Francisco seeks exceptional researchers to push the frontier of safety mitigations, helping derisk frontier models and advance techniques from interpretability, robustness and alignment to ensure safe deployments.

This role requires deep technical experience, 2+ years in AI safety and a PhD or equivalent, plus 4+ years of research engineering with Python. You will define an end‑to‑end safety stack and collaborate across domains to advance safe AGI.

Qualifications

• 2+ years of AI safety experience, including RLHF, human-AI collaboration, interpretability or control.
• PhD or equivalent in computer science, machine learning, or related field.
• 4+ years of research engineering experience with Python or similar languages.

Responsibilities

• Identify emerging AI safety risks and mitigation methods.
• Build and refine evaluations with domain experts to assess risks.
• Set research directions to improve safety, alignment, and robustness.
• Contribute to developing best practices for AI safety across the industry.
• Evaluate end‑to‑end safety pipelines and identify areas for improvement.

Skills

RLHF

Human-AI collaboration

Interpretability

Control

Python

Education

PhD in CS/ML or related field

Job description

OpenAI in San Francisco seeks exceptional researchers to push the frontier of safety mitigations, helping derisk frontier models and advance techniques from interpretability, robustness and alignment to ensure safe deployments.

This role requires deep technical experience, 2+ years in AI safety and a PhD or equivalent, plus 4+ years of research engineering with Python. You will define an end‑to‑end safety stack and collaborate across domains to advance safe AGI.