Research Scientist, AGI Safety and Alignment
Google DeepMind · London, UK
CHECKED 23H AGO
Frontier labonsitemid-level
At a glance
Highlights
- Research novel alignment techniques to reduce existential and catastrophic AGI risk.
- Build control systems for agents as defense against misaligned internal deployments.
- Advise executive leadership on AI risks via frontier safety framework.
Ideal candidate
Research-minded engineer with ML research experience who cares deeply about AGI safety and wants to turn alignment theory into real safeguards for frontier models.
Requirements
- Bachelor's degree in Computer Science, related field, or equivalent practical experience
- 3 years of experience in software development, ML engineering, or ML research
- Experience working with research teams
- Experience conducting or contributing to applied research on safety and alignment of frontier AI systems (preferred)
- Experience with training large models including supervised finetuning and RLHF (preferred)
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)