Frontier AI Security Research Lead & Engineering Manager

Google DeepMind; San Francisco (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind seeks a highly experienced Software Engineer focused on cybersecurity and AI safety. The role sits within the cyberattack safety team and involves building defenses for frontier models, conducting adversarial research, and collaborating with safety engineers to enhance Gemini’s cyber defenses.

You will apply engineering, ML, RL, and cybersecurity knowledge to create scalable, secure software, from research prototypes to production-ready infrastructure, impacting Gemini releases

Qualifications

• PhD in Computer Science or related field.
• 5 years of cybersecurity experience (red teaming, vulnerability IDs, reverse engineering, etc.).
• 5 years developing agentic tools.
• 2 years of people management experience.

Responsibilities

• Improve adversarial evaluation techniques (auto-red teaming).
• Drive defenses for out-of-model systems and introspection probes.
• Collaborate with safety engineering on adversarial research capabilities.
• Contribute to Gemini’s cyber defense capabilities.
• Bridge research to production for Gemini releases and user impact.

Skills

Cybersecurity experience

Agentic tools development

People management

Education

PhD in Computer Science or related field

Job description

Google DeepMind seeks a highly experienced Software Engineer focused on cybersecurity and AI safety. The role sits within the cyberattack safety team and involves building defenses for frontier models, conducting adversarial research, and collaborating with safety engineers to enhance Gemini’s cyber defenses.

You will apply engineering, ML, RL, and cybersecurity knowledge to create scalable, secure software, from research prototypes to production-ready infrastructure, impacting Gemini releases