Research Engineer, Agentic AI Security & Privacy

DeepMind Technologies Limited; San Francisco (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind in San Francisco is seeking a research-focused Software Engineer to embed within the team, running large-scale experiments and prototyping architectures that advance Gemini and broader AI safety initiatives.

You will collaborate across teams to improve security, privacy, and adversarial evaluation while publishing findings and contributing reusable libraries, tools, and open-source resources for the company.

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 readable and reusable ML software.

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.

Skills

Generative models training

ML safety / alignment

Python programming

Readable ML software

Education

Master's degree in Computer Science or related quantitative field

Tools

JAX

PyTorch

Job description

Google DeepMind in San Francisco is seeking a research-focused Software Engineer to embed within the team, running large-scale experiments and prototyping architectures that advance Gemini and broader AI safety initiatives.

You will collaborate across teams to improve security, privacy, and adversarial evaluation while publishing findings and contributing reusable libraries, tools, and open-source resources for the company.