Research Fellow / Phd Candidate in Ai Safety & Alignment

**Institution**: AI Security and Safety Department, Simula Cybersecurity, Oslo, Norway
**The Opportunity**
As general-purpose AI systems become more integrated into society, ensuring their safety and alignment with human values is paramount. Simula Cybersecurity is looking for a dedicated researcher to lead our efforts in **AI safety red teaming**. This role is a chance to define and advance the methodologies for preventing unintended, harmful behaviors in open-source AI models. Your work will focus on the foundational challenges of safety, from mitigating algorithmic bias to ensuring systems remain controllable and transparent.
This is a unique opportunity to shape the future of trustworthy AI alongside world-class researchers in Oslo, Norway.
**Research Focus Areas**
- **Red Teaming Framework for AI Safety**: Create a novel, comprehensive framework for assessing and mitigating AI safety risks. This involves moving beyond ad-hoc testing to a systematic, scenario-based a...