Job description

At Google, research-focused Software Engineers are embedded throughout the company, allowing them to setup large-scale tests and deploy promising ideas quickly and broadly. Ideas may come from internal projects as well as from collaborations with research programs at partner universities and technical institutes all over the world. From creating experiments and prototyping implementations to designing new architectures, engineers work on real-world problems including artificial intelligence, data mining, natural language processing, hardware and software performance analysis, improving compilers for mobile platforms, as well as core search and much more. But you stay connected to your research roots as an active contributor to the wider research community by partnering with universities and publishing papers. In this role, you will build solutions that enable us to protect the world from misuse of the next generation of frontier models and help defend against emerging cyber security risks. Capable cybersecurity models, combined with a sophisticated harness, you will present ongoing challenges that require better defenses. You will apply engineering, ML, RL, and cybersecurity knowledge to make software more secure, building both research prototypes and robust, scalable infrastructure. You will be a member of the cyberattack safety team, which is currently developing defenses for preventing misuse of our models for cyberattack as well as contributing to increasing Gemini’s capabilities for cyber defense. Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority. We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort. Individual pay is determined by factors including job-related skills, experience, and relevant education or training. US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits Learn more about benefits at Google . • Improve our adversarial evaluation (auto-red teaming) techniques. • Drive improvements for out-of-model defenses such as classifiers and introspection probes. • Collaborate with safety engineering to develop new capabilities based on adversarial research. • Contribute to increasing Gemini’s capabilities for cyber defense. • Gain an understanding of the path from research to production while working on real world problems. Your work will directly impact Gemini releases and users. • PhD degree in Computer Science, a related field, or equivalent practical experience. • 5 years of experience in cybersecurity (e.g., red teaming, vulnerability identification, reverse engineering, black-box evaluation, etc.). • 5 years of experience developing agentic tools. • 2 years of experience as a people manager. Minimum qualifications: • PhD degree in Computer Science, a related field, or equivalent practical experience. • 5 years of experience in cybersecurity (e.g., red teaming, vulnerability identification, reverse engineering, black-box evaluation, etc.). • 5 years of experience developing agentic tools. • 2 years of experience as a people manager. Preferred qualifications: • 2 years of experience in software development or engineering. • Track record of research or engineering achievements, such as publications in peer-reviewed conferences or journals. • Passion for AI technology and all of its possibilities.

Requirements

Must-haves

You will apply engineering, ML, RL, and cybersecurity knowledge to make software more secure, building both research prototypes and robust, scalable infrastructure.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
Learn more about benefits at Google .
Improve our adversarial evaluation (auto-red teaming) techniques.
Drive improvements for out-of-model defenses such as classifiers and introspection probes.
Collaborate with safety engineering to develop new capabilities based on adversarial research.
Contribute to increasing Gemini’s capabilities for cyber defense.
Gain an understanding of the path from research to production while working on real world problems. Your work will directly impact Gemini releases and users.
PhD degree in Computer Science, a related field, or equivalent practical experience.
5 years of experience in cybersecurity (e.g., red teaming, vulnerability identification, reverse engineering, black-box evaluation, etc.).
5 years of experience developing agentic tools.
2 years of experience as a people manager.
PhD degree in Computer Science, a related field, or equivalent practical experience.
5 years of experience in cybersecurity (e.g., red teaming, vulnerability identification, reverse engineering, black-box evaluation, etc.).
5 years of experience developing agentic tools.
2 years of experience as a people manager.
2 years of experience in software development or engineering.

Nice-to-haves

US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits
Track record of research or engineering achievements, such as publications in peer-reviewed conferences or journals.
Passion for AI technology and all of its possibilities.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

mlai

Platform: google
Effort: medium