> Markdown version of [/jobs/ext/4234915-research-engineer-agentic-security-for-gemini-deepmind](https://www.wearedevelopers.com/jobs/ext/4234915-research-engineer-agentic-security-for-gemini-deepmind). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Research Engineer, Agentic Security for Gemini, DeepMind

- **Company:** Google LLC
- **Location:** San Francisco, CA, United States
- **Salary:** $174,000.0 - $252,000.0
- **Contract:** Permanent contract
- **Skills:** Training Data, Python (Programming Language), Machine Learning, Open Source Technology, Pytorch, Agentic-AI, Information Technology, Google Gemini, DeepMind
- **Published:** October 7, 2026
- **Apply:** https://dejobs.org/x/x/4E2DF0F870094BE1A06208B3F33C2E51/job/

## About the Role

* 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 readabl and reusable ML software.

Preferred qualifications:

 * Experience with JAX, PyTorch, or similar machine learning platforms.
 * Experience in Python through strong artifacts in building readable, scalable, reusable ML software.

## Description

* 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.