Search
Go
Research Engineer, AI Safety & Alignment
MADRID · ES
—
Full-time
About the Role
This is a research engineer role focusing on AI safety and alignment. The position involves developing evaluation metrics, conducting adversarial testing, mitigating biases, and integrating safety solutions into products.
Responsibilities
- Develop evaluation metrics for AI safety
- Conduct adversarial testing of AI models
- Mitigate biases in AI systems
- Integrate safety solutions into products
Requirements
- Experience with interpretability techniques
- Research background in AI safety or alignment
C
Careerium
New Providence · BS · 1+ employees
CareeRium is a professional training and coaching service provider. The company specializes in CV making, reviewing, and upgrading, as well as LinkedIn profile optimization and career consultation.
