Frontier Safety Mitigations Research Engineer
Google DeepMind · London, UK
CHECKED 23H AGO
Frontier labonsite
At a glance
Highlights
- Build advanced classifiers to detect misuse from evaluation to rapid iteration.
- Develop cross-context monitoring to uncover coordinated large-scale attacks.
- Secure agentic AI by threat modeling frontier-level hacking attacks.
Ideal candidate
Safety-minded engineer with deep applied ML experience who thrives taking research mitigations to production and cares about defending frontier AI from misuse and agentic attacks.
Requirements
- Bachelor's degree in Computer Science, Machine Learning, or a related technical field, or equivalent practical experience.
- 5 years of experience in software development, including experience with Python.
- Experience with the research-to-deployment pipeline in a frontier AI environment.
- Experience working in a software engineering or research team.
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)