Research Engineer, AI Security & Privacy

The Safety Systems team at OpenAI is seeking a Research Engineer for AI Security & Privacy to pioneer methodologies and implement systems to reduce risks in AI security and privacy during model deployment. This role involves designing, implementing, and evaluating novel methods to protect AI models from threats such as data extraction and model inversion attacks. You'll collaborate with cross-functional teams, especially the Post Training team, to integrate privacy-preserving techniques into AI model development and establish security and privacy best practices for model deployment.

Key responsibilities include:

• Researching and implementing solutions to mitigate risks associated with data poisoning, membership inference attacks, and more.
• Leading efforts in AI security and privacy research for deep learning models.
• Collaborating closely with various teams to improve AI security and privacy protection of OpenAI's models and systems.

The ideal candidate should:

• Be strongly motivated by OpenAI's mission and aligned with their charter.
• Hold a Ph.D. or other degree in computer science, AI, machine learning, or a related field.
• Have 3+ years of experience in AI security and privacy research for deep learning models.
• Possess an in-depth understanding of deep learning research and strong engineering skills, particularly in Python and PyTorch.
• Stay goal-oriented and be willing to tackle high-value work when needed.
• Be a team player who enjoys collaborative work environments.

This role is based in San Francisco, CA, with a hybrid work model of 3 days in the office per week. OpenAI offers relocation assistance to new employees and is committed to diversity, equal opportunity, and providing reasonable accommodations to applicants with disabilities.