Research Scientist, Harmful Manipulation
Google DeepMind · New York, NY, USA · London, UK · Mountain View, CA, USA
Frontier labonsite$174k–$252k
At a glance
Highlights
- Research emerging manipulation risks and develop novel evaluations for frontier AI.
- Probe how advanced AI models influence users to inform mitigation and governance.
- Publish novel methodologies and engage external safety institutes and experts.
What they offer
- 15% bonus target
- equity
- benefits
Ideal candidate
PhD-level researcher fascinated by technology-driven persuasion and manipulation who wants to translate rigorous evaluations into safer frontier AI through cross-functional collaboration.
Requirements
- PhD in Psychology, Political Science, Computational Social Science, Computer Science, related field or equivalent experience
- Experience designing evaluations or studies on technology and manipulation, persuasion or social engineering
- Track record driving complex projects including in research settings
- Publications in high-impact venues such as NeurIPS, CHI, FAccT
- Ability to leverage AI tools to build and accelerate research pipelines or safety benchmarks
- Commitment to translating research into practice and working cross-functionally
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)
Posted · Last seen