Gemini Safety Research Engineer - Post-Training AI Alignment

DeepMind

Mountain View (CA)

On-site

USD 174,000 - 252,000

Full time

46 hours ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Equity
Bonus target

Job summary

Google DeepMind in Mountain View seeks a Research Engineer for Gemini Agent Safety Post Training to design and deploy alignment mechanisms, sandbox behaviors, and trajectory-level training for Gemini agents to operate safely and reliably at global scale.

You will collaborate within the GenAI Alignment and Safety teams, partnering with pre-training, mid-training, post-training, and product engineering to ensure safety foundations across the Gemini model family and broader AI ecosystem.

Qualifications

  • Bachelor’s degree or equivalent practical experience required.
  • 2 years of software development or ML research experience or education equivalent (internships, student research, pre-graduate experience).
  • Experience in machine learning algorithms, deep learning research, and large language modeling.

Responsibilities

  • Design, implement, and maintain alignment mechanisms, sandbox behaviors, and trajectory-level training for Gemini agents at scale.
  • Collaborate with post-training, evaluation, and product teams to anchor safety foundations in Google’s AI ecosystem.
  • Pioneer safety alignment algorithms and dynamic evaluations and drive technical execution to deploy models across production surfaces.
  • Contribute to safe and reliable AI across frontier reasoning models and deep research architectures.

Skills

ML research
Software development
Deep learning

Education

Bachelor’s degree or equivalent practical experience

Job description

Google DeepMind in Mountain View seeks a Research Engineer for Gemini Agent Safety Post Training to design and deploy alignment mechanisms, sandbox behaviors, and trajectory-level training for Gemini agents to operate safely and reliably at global scale.

You will collaborate within the GenAI Alignment and Safety teams, partnering with pre-training, mid-training, post-training, and product engineering to ensure safety foundations across the Gemini model family and broader AI ecosystem.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Scientist, AI Safety & Alignment (Post-Training)
Research Scientist, AI Safety & Alignment (Post-Training)

DeepMind • Mountain View (CA)

On-site
USD 207,000 - 300,000
Research Scientist, AI Safety & Alignment (Post-Training)
Research Scientist, AI Safety & Alignment (Post-Training)

Google LLC • Mountain View (CA)

On-site
USD 174,000 - 252,000
AI Safety & Alignment Research Scientist
AI Safety & Alignment Research Scientist

DeepMind Technologies Limited • Mountain View (CA)

On-site
USD 174,000 - 252,000
Senior AI Safety and Alignment Research Scientist
Senior AI Safety and Alignment Research Scientist

Google DeepMind • Mountain View (CA)

On-site
USD 207,000 - 300,000
Safety & Behavior Scientist for Gemini AI Systems
Safety & Behavior Scientist for Gemini AI Systems

Google LLC • New York (NY)

On-site
USD 207,000 - 300,000
Equity
Bonus target
Research Scientist, Gemini Agent Safety Post Training, DeepMind
Research Scientist, Gemini Agent Safety Post Training, DeepMind

Google DeepMind • Mountain View (CA)

On-site
USD 207,000 - 300,000
Research Scientist, Gemini Agent Safety, DeepMind
Research Scientist, Gemini Agent Safety, DeepMind

DeepMind Technologies Limited • Mountain View (CA)

On-site
USD 174,000 - 252,000
Research Scientist, Gemini Agent Safety
Research Scientist, Gemini Agent Safety

Google LLC • Mountain View (CA)

On-site
USD 174,000 - 252,000
Research Engineer, Gemini Agent Safety Post Training, DeepMind
Research Engineer, Gemini Agent Safety Post Training, DeepMind

DeepMind • Mountain View (CA)

On-site
USD 174,000 - 252,000
Equity
Bonus target
Research Engineer, Agentic Security for Gemini AI
Research Engineer, Agentic Security for Gemini AI

DeepMind Technologies Limited • Mountain View (CA)

On-site
USD 174,000 - 252,000