Research Engineer, Gemini Cyber Post-Training, DeepMind
Google· DeepMind
Remote$147k - $210kfull-timePosted 3d ago
About the role
Research Engineer role focused on cyber security within the Gemini team at DeepMind, contributing to vulnerability discovery, post-training recipes, and scalable infrastructure for AI safety and security initiatives.
Responsibilities
- Build datasets (RL environments, SFT data) and iterate on post-training recipes.
- Debug and analyze RL training runs to identify potential bottlenecks and optimize training efficiency and effectiveness.
- Build evaluation pipelines, benchmarks, and leaderboards to measure agent performance.
Qualifications
- PhD degree in Computer Science, or a related field, or equivalent practical experience.
- 2 years of experience (industry or academia) working in Reinforcement Learning environments.
- Experience building distributed system infrastructure.
- One or more publication records in vulnerability research (e.g. auditing, reverse engineering, exploitation).
Skills
Required:Reinforcement LearningDistributed systemsDatasets and data pipelinesEvaluation and benchmarking
Benefits
- Equity is granted exclusively and discretionarily by Alphabet Inc. on the basis of an agreement concluded between you and Alphabet Inc.
- 15% bonus target + equity + benefits (US base)
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