Research Engineer, Agentic Security for Gemini, DeepMind

Minimum qualifications:

• Master's degree in Computer Science or related quantitative field.
• 1 year of experience in training or fine-tuning generative models to improve capabilities.
• Experience in one of the machine learning safety, security, privacy, or alignment fields.
• Experience in one machine learning framework such as JAX or PyTorch.
• Experience building readabl and reusable ML software.

Preferred qualifications:

• Experience with JAX, PyTorch, or similar machine learning platforms.
• Experience in Python through strong artifacts in building readable, scalable, reusable ML software.

About the job:

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.

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.

Responsibilities:

• Build post-training data and tools to improve Gemini's security & privacy capabilities across coding, personal assistant, and other agentic capabilities; integrating improvements into latest versions of Gemini.
• Coordinate closely with stakeholders working on Gemini's tool use, coding and other agentic capabilities to ensure security & privacy gains in the model do not impact Gemini's utility.
• Collaborate with other team members to improve our adversarial evaluation (auto-red teaming) techniques and out-of-model guardrails.
• Amplify the impact by generalizing solutions into reusable libraries and frameworks for protecting agents and models across Google, and by sharing knowledge through publications, open source, and education.