Job Summary:
Google DeepMind is a pioneering AI lab focused on advancing AI development to solve complex global challenges. They are seeking a Research Engineer for Agentic Security & Privacy Post-Training for Gemini, responsible for building training data and techniques to enhance security and privacy capabilities in generative AI models.
Responsibilities:
โข 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.
โข 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.
โข Collaborate with other team members to improve our adversarial evaluation (auto-red teaming) techniques and out-of-model guardrails.
โข 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.
Qualifications:
Required:
โข Bachelorโs degree or equivalent practical experience.
โข 5 years of experience with software development in one or more programming languages.
โข 3 years of experience testing, maintaining, or launching software products, and 1 year of experience with software design and architecture.
Preferred:
โข Master's degree in Computer Science or related quantitative field with 5 years of relevant experience.
โข Experience in Python through strong artifacts in building readable, scalable, reusable ML software.
โข Experience in training or fine-tuning generative models to improve capabilities.
โข Experience in solving machine learning security and privacy problems.
โข Experience with JAX, PyTorch, or similar machine learning platforms.
Company:
Google DeepMind aims to research and build safe artificial intelligence system to solve intelligence and advance science and humanity. It is a sub-organization of Google. Founded in 2010, the company is headquartered in London, GBR, with a team of 501-1000 employees. The company is currently Late Stage.