10 hours ago
Base Salary
$174k - $252k/yr
Responsibilities
- Build post-training data and tools to improve Gemini’s security and privacy capabilities across coding, personal assistant, and other agentic capabilities.
- Integrate security and privacy improvements into current versions of Gemini.
- Coordinate with stakeholders working on Gemini’s tool use, coding, and other agentic capabilities to preserve model utility.
- Improve adversarial evaluation and automated red-teaming techniques and develop out-of-model guardrails.
- Generalize solutions into reusable libraries and frameworks for protecting agents and models across Google.
- Share knowledge through publications, open source, and education.
Requirements
- Master’s degree in Computer Science or a related quantitative field.
- At least 1 year of experience 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.
- Preferred: experience with JAX, PyTorch, or similar machine learning platforms.
- Preferred: experience with Python demonstrated through readable, scalable, reusable ML software artifacts.
Categories
AI ResearchML Engineering
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.