About The Role

"<1.Be> responsible for the research on the security and alignment of AI models
2.Develop a model safety assessment and risk control mechanism
3.Ensure that AI systems comply with ethical norms and regulatory requirements
4.Establish an AI security protection system to prevent potential risks"
"More than 3 years of research experience in AI security or machine learning, with a deep understanding of the security risks and ethical issues of large models.

Proficient in cutting-edge technologies such as Red team testing, adversarial attack and defense, and model interpretability.
Be capable of independently establishing a comprehensive AI security assessment system and writing security alignment technical reports.
Excellent cross-departmental communication skills, capable of closely collaborating with the legal and compliance teams."

This is an external listing. JobSpring does not represent or verify the employer. Report this listing

Research Scientist, AI Safety & Alignment(J31971)