Introspection Probe Research Engineer, Development and Infrastructure, Gemini Security
Google DeepMind · Mountain View, CA, USA · New York, NY, USA · San Francisco, CA, USA
CHECKED 23H AGO
Frontier labonsite$174k–$252k
At a glance
Highlights
- Build detection methods to protect Gemini from unauthorized distillation.
- Research and land improvements for Gemini security introspection heads.
- Partner with introspection team to improve training, serving and deployments.
What they offer
- 15% bonus target
- equity
- benefits
Ideal candidate
A research-driven engineer passionate about AI safety and real-world impact, who communicates exceptionally and thrives influencing cross-functional partners to protect frontier models.
Requirements
- Bachelor's degree in Computer Science or related technical 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 experience in software development or engineering
- Experience building real-time interventions for security, safety or anti-abuse in large-scale AI systems
Lab profile
About Google DeepMind
Google's AI lab building frontier models like Gemini to advance science and general intelligence.
What they build
- Gemini
- Gemma
- AlphaFold
Known for
- Frontier foundation models and GenAI
- Large-scale training with JAX, PyTorch, TensorFlow
- Model evaluation and deployment expertise
- Responsible frontier AI research
Key facts
- Founded in 2010
- Headquartered in London, UK
- Part of Google (Alphabet)