Threat Modeling Lead, Harmful Manipulation
Google DeepMind · New York, NY, USA · London, UK · Mountain View, CA, USA
Frontier labonsiteLead$207k–$300k
At a glance
Highlights
- Shape deployment safeguards and safety launch thresholds for frontier AI models.
- Design evaluations probing how advanced AI models influence and manipulate users.
- Engage governments and safety institutes on frontier AI manipulation risks.
What they offer
- 20% bonus target
- equity
- benefits
Ideal candidate
Threat intelligence-minded researcher fascinated by persuasion and influence operations, eager to translate complex risks into safeguards that protect the global digital ecosystem from scaled AI misuse.
Requirements
- PhD in Computer Science, Political Science, Psychology, Computational Social Science, related field or equivalent industry experience
- Experience performing technical work such as OSINT data collection, API scraping, log analysis and data analysis
- Experience studying mechanics of human manipulation, persuasion, propaganda, influence operations or social engineering
- Experience in a national lab, government, military intelligence unit, frontier lab threat intelligence team or research institution
- Ability to translate complex intelligence and technical risks into actionable insights for leaders and policymakers
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