AI Research Scientist

About the Role

The FAIR Security, Privacy, and Reliability team conducts fundamental research to discover novel attacks, measure privacy, and find non-intuitive breaks in robustness for AI agents and foundational models. This includes contributing benchmarks to Meta's model Evaluation Reports and publishing research in top venues. The team also develops and implements novel post-training mitigations for these risks, with opportunities for direct research-to-production translation.

Key Responsibilities

• Conduct fundamental research to discover novel safety and security failures, robust approaches to measuring memorization risk or reliability failures in AI agents and foundational models.
• Develop and contribute benchmarks to Meta's foundational model evaluation suite and/or the Evaluation Reports.
• Design and implement novel post-training mitigations for safety, security, privacy, and reliability risks in foundation models.
• Collaborate with cross-functional teams to translate research into production systems.

Requirements & Tech Stack

• Research experience in at least one of the following areas:
• safety, security, privacy, or robustness of AI models
• adversarial machine learning
• indirect prompt injections or jailbreaks
• contextual integrity or memorization
• reward hacking or other agent reliability failures
• testing or mitigating foundation models for catastrophic risk (CBRNE, cyber, loss of control)
• developing mitigations in any of these areas.

Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience.
• PhD in Computer Science, Machine Learning, or related field, or equivalent practical experience.
• Preferred: Track record of publications in top-tier research venues.