Research Scientist/Engineer, Autonomous Security, DeepMind

About the role

Research role applying foundation-model post-training and autonomous agents to cybersecurity, with work on Gemini, simulated security workflows, synthetic data, adversarial planning, evaluation benchmarks, and deployment. Sponsorship is unstated.

Requirements

• PhD in computer science, cybersecurity, machine learning, related field, or equivalent practical experience
• 4 years Python and ML frameworks training, fine-tuning, and evaluating foundation models
• 3 years applying ML or automated reasoning to cybersecurity, systems, program analysis, or code generation
• 2 years LLM post-training with SFT, execution-feedback reinforcement learning, and multi-step trajectory reward modeling
• Preferred experience architecting autonomous agents and building simulated execution environments, evaluation harnesses, or synthetic-data pipelines
• Preferred cybersecurity expertise and ML or security publications or production deployment

What you'll do

• Design and iterate on Gemini post-training methods
• Build simulated environments and synthetic-data pipelines for security workflows
• Architect autonomous security agent harnesses
• Develop offensive, defensive, and vulnerability evaluation benchmarks
• Move research into internal defenses and customer products

Where this was posted

• LinkedIn

  last seen 2h ago
  View on LinkedIn