Research Scientist, Model Safety - job 2 of 2

About the Team

The Safety Systems team is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit the society and is at the forefront of OpenAI's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency.

The Model Safety Research team aims to fundamentally advance our capabilities for precisely implementing robust, safe behavior in AI models, and to leverage these advances to make OpenAI’s deployed models safe and beneficial.  This requires a breadth of new ML research to address the growing set of safety challenges as AI becomes more powerful and used in more settings.  Key focus areas include how to enforce nuanced safety policies without trading off helpfulness and capabilities, how to make the model robust to adversaries, how to address privacy and security risks, and how to make the model trustworthy in safety-critical domains.   

We seek to learn from deployment and distribute the benefits of AI, while ensuring that this powerful tool is used responsibly and safely. 

About the Role

OpenAI is seeking a senior researcher with passion for AI safety and experience in safety research. Your role will set directions for research to enable and empower safe AGI and work on research projects to make our AI systems safer, more aligned and more robust to adversarial or malicious use cases. You will play a critical role in shaping how a safe AI system should look like in the future at OpenAI, making a significant impact on our mission to build and deploy safe AGI.

In this role, you will:

• Conduct state-of-the-art research on AI safety topics such as RLHF, adversarial training, robustness, and more.
• Implement new methods in OpenAI’s core model training and launch safety improvements in OpenAI’s products.
• Set the research directions and strategies to make our AI systems safer, more aligned and more robust.
• Coordinate and collaborate with cross-functional teams, including T&S, legal, policy and other research teams, to ensure that our products meet the highest safety standards.
• Actively evaluate and understand the safety of our models and systems, identifying areas of risk and proposing mitigation strategies.

You might thrive in this role if you:

• Are excited about OpenAI’s mission of building safe, universally beneficial AGI and are aligned with OpenAI’s charter
• Demonstrate a passion for AI safety and making cutting-edge AI models safer for real-world use.
• Bring 4+ years of experience in the field of AI safety, especially in areas like RLHF, adversarial training, robustness, fairness & biases.
• Hold a Ph.D. or other degree in computer science, machine learning, or a related field.
• Possess experience in safety work for AI model deployment
• Have an in-depth understanding of deep learning research and/or strong engineering skills.
• Are a team player who enjoys collaborative work environments.