Real-Time AI Security Research Engineer

AI Chopping Block, Inc.; Mountain View, Northern (CA, KY); Hybrid; USD 174,000 - 252,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

Google is seeking a Research Engineer for the Gemini Security team in Mountain View to develop detection methods and real-time interventions protecting Gemini from unauthorized distillation.

You will work on large-scale LLM training and serving infrastructure, deploy security classifiers, and collaborate with universities and internal teams to publish research and advance AI safety and security measures.

Qualifications

• Bachelor's degree in Computer Science or related field, or equivalent practical experience.
• Experience with large-scale LLM training and serving infrastructure.
• Experience training security or safety classifiers for large AI models.
• Experience deploying security or safety classifiers.
• 2 years of software development or engineering experience.
• Experience building real-time interventions for security in large-scale AI systems.
• Exceptional communication skills with the ability to influence cross-functional stakeholders and executives.
• A deep passion for AI technology and all of its possibilities.

Responsibilities

• Research, build and land improvements for Gemini security introspection heads.
• Research, build and land real-time interventions triggered by introspection heads.
• Partner with introspection team to improve heads training, serving and deployments.

Skills

LLM training

Security classifiers

Real-time interventions

Software development

Cross-functional comms

Research collaboration

Education

Bachelor's degree in CS or related field

Job description

Google is seeking a Research Engineer for the Gemini Security team in Mountain View to develop detection methods and real-time interventions protecting Gemini from unauthorized distillation.

You will work on large-scale LLM training and serving infrastructure, deploy security classifiers, and collaborate with universities and internal teams to publish research and advance AI safety and security measures.