Agentic-Security Research Engineer (ML Safety & Privacy)

Google; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google is seeking a research-focused Software Engineer to work on Gemini's security and privacy improvements. You will be embedded across teams to prototype and deploy scalable AI capabilities, partnering with researchers and engineers worldwide.

From experiments to architectures, you will push safety and alignment while contributing to reusable libraries, open-source projects, and publications that advance responsible AI at scale.

Qualifications

• Master's degree in Computer Science or related field.
• 1 year of experience training or fine-tuning generative models.
• Experience in ML safety, security, privacy, or alignment.
• Experience with 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

ML Training Experience

ML Safety

Readable ML Software

Python Proficiency

Education

Master's degree in CS or related field

Tools

JAX

PyTorch

Job description

Google is seeking a research-focused Software Engineer to work on Gemini's security and privacy improvements. You will be embedded across teams to prototype and deploy scalable AI capabilities, partnering with researchers and engineers worldwide.

From experiments to architectures, you will push safety and alignment while contributing to reusable libraries, open-source projects, and publications that advance responsible AI at scale.