Research Scientist, AI Safety and Alignment
Google DeepMind · Seattle, WA, USA
Frontier labonsite$174k–$252k
At a glance
Highlights
- Diagnose machine behavior to make frontier models safe and reliable for users.
- Solve real vulnerabilities in live systems while tackling long-term safety questions.
- Share research findings to advance AI safety across Google and the wider community.
What they offer
- 15% bonus target
- equity
- benefits
Ideal candidate
A research-minded scientist passionate about AI safety who thrives translating theory into real-world protections. You value independent thinking, interdisciplinary collaboration, and making frontier models trustworthy for billions of users.
Requirements
- PhD in Computer Science, Machine Learning, AI, Mathematics, Physics or related STEM
- 1 year of experience initiating, scoping and executing research in AI safety, alignment or interpretability
- Experience evaluating, steering, red teaming or implementing safeguards on LLMs or frontier systems
- Experience in Python or C++, deep learning frameworks and agentic workflows
- First-author publications at NeurIPS, ICML, ICLR or COLM
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)
First seen · Last seen