# Research Scientist, Gemini Agent Safety Post Training, DeepMind at Google

- Company: Google
- What the company does: Learn more about Google. Explore our innovative AI products and services, and how we. Backed by Kleiner Perkins.
- Company website: https://about.google/
- Type: Startups (AI role)
- Level: Mid level
- Location: United States
- Work setup: On-site
- Posted: 2026-11-11
- Apply by: 2026-12-26
- Apply: https://www.google.com/about/careers/applications/jobs/results/93464074288800454-research-scientist-gemini-agent-safety-post-training-deepmind?utm_source=1752vc&utm_medium=careers
- Page: https://www.1752.vc/careers/jobs/google-research-scientist-gemini-agent-safety-post-training-deepmind/

## About the role

The Gemini Safety team is accountable for the standards of GDM’s flagship releases. In this role, you will develop algorithmic solutions to advance user-facing architectures. The workstyle is changing, supported by a strong internal culture of mutual dedication and cooperation. You will bring a Large Language Model (LLM) post-training expertise to ensure outputs are aligned and production-ready. You will be a builder and shipper who takes end-to-end ownership. Found on 1752vc Careers, the job board for startup and VC roles.

## What they're looking for

- PhD in Computer Science, a related field, or equivalent practical experience
- 3 years of experience initiating, scoping, and executing research agendas or leading academic projects
- One or more peer-reviewed scientific publication submissions (e.g., NeurIPS, ICML, ICLR, CVPR, ACL, CoRL) or public preprint repositories (arXiv)


Source: 1752vc Careers, https://www.1752.vc/careers/jobs/google-research-scientist-gemini-agent-safety-post-training-deepmind/
