Research Engineer, Agentic Security for Gemini
$174k - $252k • Mountain View, CA, USA; San Francisco, CA, USA • Full-time
Posted 1mo ago
Job Location
Mountain View, CA, USA; San Francisco, CA, USA
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
At Google DeepMind, we are a pioneering AI lab 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. This role involves building post-training data and tools to improve Gemini's security and privacy capabilities, integrating improvements into the latest versions of Gemini, and collaborating with stakeholders to ensure security and privacy gains do not impact utility. The position also focuses on improving adversarial evaluation techniques and generalizing solutions into reusable libraries and frameworks for protecting agents and models across Google.
Responsibilities
- Build post-training data and tools to improve Gemini's security and privacy capabilities across coding, personal assistant, and other agentic capabilities, integrating improvements into the latest versions of Gemini.
- Coordinate with stakeholders working on Gemini's tool use, coding, and other agentic capabilities to ensure security and privacy gains do not impact Gemini's utility.
- Collaborate with team members to improve adversarial evaluation (auto-red teaming) techniques and out-of-model guardrails.
- Amplify 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.
Requirements
- 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 machine learning safety, security, privacy, or alignment.
- Experience with a machine learning framework such as JAX or PyTorch.
- Experience building readable and reusable ML software.
- Experience with JAX, PyTorch, or similar machine learning platforms.
- Experience in Python through strong artifacts in building readable, scalable, reusable ML software.
Benefits
- 15% bonus target
- Equity
- Benefits
