Job Description
The AI Security Institute is seeking a highly motivated and talented Research Scientist/Research Engineer to join its Safeguard Analysis Team. This team focuses on researching and evaluating interventions, known as 'safeguards,' to secure advanced AI systems from abuse. The role involves a broad view of security threats and interventions, welcoming diverse perspectives from various security disciplines.
Role Involves: - Assessing threats to frontier AI systems.
- Developing novel attacks and protections for systems based on large language models.
- Building infrastructure for running evaluations.
- Mentoring and coaching from managers and technical leads.
- Interacting with world-renowned researchers.
Requirements: - Experience in machine learning, AI security, computer security, or related security disciplines.
- Experience working with a world-class research team.
- Red-teaming experience.
- Strong written and verbal communication skills.
- Comprehensive understanding of large language models.
- Extensive Python experience.
- Ability to work self-directed and thrive in a changing environment.
- Eagerness to support colleagues and contribute to the team's success.
- Sense of mission, urgency, and responsibility.
- Writing production quality code.
- Improving technical standards through mentoring and feedback.
- Designing, shipping, and maintaining complex tech products.
Role Offers: - Mentorship and coaching.
- Interaction with world-famous researchers.