- Copenhagen, Capital Region, Denmark
- On-site
- Full-time · Staff
Key part of the team building Halfspace’s technical AI Safety capabilities, defining best practices for building safe and secure agentic AI systems across rigorous evaluation, threat and risk modelling, control design, and robust system architectures.
Responsibilities
- Define best practices for building safe and secure agentic AI systems
- Work with leadership and commercial leads to shape safety offering
- Lead Safety-focused client engagements
- Mentor junior colleagues
Requirements
- MSc or PhD in a STEM field such as computer science, machine learning, mathematics, statistics, physics or engineering
- Equivalent practical experience
- Nice to have: Consulting experience
- Nice to have: Knowledge of EU AI Act
- Nice to have: Knowledge of ISO 42001