Frontier AI Cybersecurity Risk Researcher

OpenAI; Los Angeles (CA); On-site; USD 295,000 - 445,000; Full time

Job summary

A leading AI research organization in Los Angeles is seeking a Researcher to mitigate cybersecurity risks associated with powerful AI models. The role involves designing and implementing innovative safeguards, collaborating cross-functionally, and evaluating technical trade-offs to ensure resiliency against evolving threats. Ideal candidates possess deep learning expertise and a passion for AI safety, with experience in frameworks like PyTorch or TensorFlow. Competitive compensation amidst a culture of diversity and inclusion is offered.

Qualifications

• Experience in designing and deploying technical safeguards for cybersecurity.
• Ability to work collaboratively with teams across various disciplines.
• Strong foundation in data structures, algorithms, and software engineering principles.

Responsibilities

• Design and implement mitigation components for cybersecurity misuse.
• Integrate safeguards across product surfaces in partnership with engineering.
• Execute rigorous testing for evolving threats across different product surfaces.

Skills

Deep learning

Transformer models

AI safety

Cross-functional collaboration

Technical safeguards for abuse prevention

Tools

PyTorch

TensorFlow

Job description

A leading AI research organization in Los Angeles is seeking a Researcher to mitigate cybersecurity risks associated with powerful AI models. The role involves designing and implementing innovative safeguards, collaborating cross-functionally, and evaluating technical trade-offs to ensure resiliency against evolving threats. Ideal candidates possess deep learning expertise and a passion for AI safety, with experience in frameworks like PyTorch or TensorFlow. Competitive compensation amidst a culture of diversity and inclusion is offered.