RSI Safety Researcher: Frontline AI Alignment Prep

OpenAI; Greater London; On-site; GBP 281,000 - 370,000; Full time

Job summary

OpenAI is seeking a strong technical executor to join the Preparedness team. This role focuses on mitigating frontier AI risks and preparing for recursive self-improvement in a fast-paced environment.

You will work on misalignment risk mitigation, design pre-deployment risk assessments, and translate technical work into scalable institutional practices and external communications.

Impactful work with broad implications for the company and society, requiring taste, strategy, and strong delivery.

Responsibilities

• Carefully consider future challenges OpenAI might face and how to prepare for them.
• Turn abstract objectives into concrete directions to guide priority work.
• Build scrappy prototypes and iteratively improve them into production components.
• Secure buy-in from staff and communicate your work clearly.
• Collaborate with or manage others to scale efforts quickly.

Job description

OpenAI is seeking a strong technical executor to join the Preparedness team. This role focuses on mitigating frontier AI risks and preparing for recursive self-improvement in a fast-paced environment.

You will work on misalignment risk mitigation, design pre-deployment risk assessments, and translate technical work into scalable institutional practices and external communications.

Impactful work with broad implications for the company and society, requiring taste, strategy, and strong delivery.