En vedette
AI Safety Researcher
Negotiable
Description du poste
Research and develop methods to ensure AI systems are safe, reliable, and aligned with human values. Critical role in building trustworthy AI.
Exigences
- PhD in AI Safety, ML, Philosophy, or related
- Published research in AI safety/alignment
- Deep understanding of AI risks
- Experience with RLHF, constitutional AI
- Strong analytical and communication skills
- Passion for responsible AI development
- Published research in AI safety/alignment
- Deep understanding of AI risks
- Experience with RLHF, constitutional AI
- Strong analytical and communication skills
- Passion for responsible AI development
Responsabilités
- Research AI alignment techniques
- Develop safety evaluation frameworks
- Red-team AI systems
- Write safety documentation and policies
- Collaborate with product and policy teams
- Engage with AI safety community
- Develop safety evaluation frameworks
- Red-team AI systems
- Write safety documentation and policies
- Collaborate with product and policy teams
- Engage with AI safety community
Avantages
- Salary £90,000 - £150,000
- Meaningful impact work
- Research freedom
- Conference attendance
- Premium benefits package
- Sabbatical opportunities
- Meaningful impact work
- Research freedom
- Conference attendance
- Premium benefits package
- Sabbatical opportunities
Aperçu du poste
Type d'emploi
Temps plein
Niveau d'expérience
Senior
Lieu
London, England, United Kingdom
Postes vacants
2
Postuler maintenant