The Research Engineer position at DeepMind focuses on security and privacy within AI systems. The role involves evaluating generative models to identify vulnerabilities and improve their robustness. Engineers will collaborate with various teams to translate research insights into practical applications. This position is integral to advancing AI development while ensuring safety and ethical considerations are prioritized.

• Bachelor’s degree or equivalent practical experience.
• 5 years of experience with software development in one or more programming languages.
• 3 years of experience testing, maintaining, or launching software products.
• 1 year of experience with software design and architecture.
• 1 year of experience in evaluating, stress-testing, or red-teaming generative models.

• Build robust pipelines, benchmarks, and auto-red teaming tools to measure model vulnerabilities.
• Collaborate closely with post-training teams to turn evaluation insights into actionable model upgrades.
• Generalize solutions into reusable evaluation libraries and frameworks for protecting agents across Google.
• Share knowledge through publications, open source, and education.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.