Applied AI Safeguards Evaluation Engineer

Blackmount.ai Inc. is seeking a research-oriented engineer in San Francisco, California. This role focuses on developing methods for safety evaluations to improve model behavior. Responsibilities include designing experiments, researching model safety factors, and analyzing evaluation coverage for potential gaps. Ideal candidates will have a background in applied machine learning research and strong engineering skills. This position offers the chance to shape safety practices in AI systems.
#J-18808-Ljbffr