Research Scientist, Frontier Computation, DeepMind
Google· DeepMind
London, UKUnknownPosted 3d ago
About the role
Research Scientist role in the Frontier Computation team at DeepMind, focusing on the relationship between neural networks and classical computation, with emphasis on safety and security in generative AI systems, long-term moonshots, and potential deployments across DeepMind offerings.
Responsibilities
- Lead long-term "moonshot" projects and direct product deployments, probe model internals, mechanistic interpretability, and information propagation with high initiative; independently design, implement, and execute rigorous empirical experiments with strict baselines and ablations.
- Take ownership of research engagements in AI security, developing prompt defenses and alignment strategies to secure frontier systems.
- Translate complex findings into clear, structured results and drive collaboration with internal and external partners.
Qualifications
- PhD degree in Computer Science, a related field, or equivalent practical experience.
- 2 years of experience with Large Language Model internals or generalization.
Skills
Required:Large Language Models internalsExperiment design and evaluation
Nice to have:Mechanistic interpretabilityAI safety and security
Last updated Oct 23, 2026. Interested? Apply on the company site.
More open roles at Google
- Staff Network Security Engineer, Google Enterprise Network3d agoHybrid (Austin, TX; Sunnyvale, CA)
- Group Product Manager, Google Lens AI Shopping3d agoMountain View, CA, USA · Product Management
- UX Program Manager3d agoHybrid (New York, NY; San Bruno, CA) · UX Programs & Operations
- Senior Staff Software Engineer, Android Automotive OS3d agoHybrid (Kraków, Poland; Munich, Germany)
- 3d ago