Research Engineer, Agentic Security for Gemini
Google DeepMind · Mountain View, CA, USA · San Francisco, CA, USA
CHECKED 22H AGO
Frontier labonsite$174k–$252k
At a glance
Highlights
- Build post-training data and tools to harden Gemini's agentic security and privacy.
- Improve auto-red teaming and guardrails to protect agents across Google.
- Integrate security gains into latest Gemini without hurting utility.
What they offer
- 15% bonus target
- equity
- benefits
Ideal candidate
Research-minded ML engineer passionate about AI safety and privacy who enjoys building robust tools and shipping security gains into real-world agents.
Requirements
- Master's degree in Computer Science or related quantitative field
- 1 year of experience in training or fine-tuning generative models to improve capabilities
- Experience in machine learning safety, security, privacy, or alignment
- Experience in a machine learning framework such as JAX or PyTorch
- Experience building readable and reusable ML software
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)