Clash
of Jobs
Browse All Jobs
Job Description
The AI Security Institute is seeking a talented Research Scientist/Engineer to join their Criminal Misuse team. This team focuses on understanding how advanced AI systems can be misused for criminal activities and societal disruption. The successful candidate will contribute to research on AI misuse in areas like fraud, scams, influence operations, and radicalization. They will build threat models, design technical evaluations, and collaborate with government and labs to develop mitigations.
Role involves:
- Conducting research on the misuse of AI for criminal activities.
- Building threat models to establish risk thresholds.
- Designing and implementing experiments to track these thresholds.
- Presenting research findings to decision-makers.
- Collaborating with a multidisciplinary team of experts.
Requirements:
- Relevant machine learning research experience.
- Understanding of large language models (e.g. GPT-4).
- Knowledge of technical safety methods.
- Strong research experience in Computer Science, AI, or a related field (e.g. PhD).
- Excellent communication skills.
- Interest in the misuse of AI systems.
Role offers:
- Opportunity to work with a talented and experienced team.
- Chance to contribute to research with direct policy impact.
- Exposure to cutting-edge AI capabilities.
