Skip to content
← Google DeepMind

Research Engineer, Chemical, Biological and Nuclear AI Safety

Google DeepMind · London, UK

Frontier labonsitesenior
Apply on the lab’s site ↗

At a glance

Highlights

  • Build novel safeguards and stress-test them with automated and manual red teaming.
  • Design evaluations for chemical, biological, and nuclear risk in frontier models.
  • Launch safety safeguards to billions of Gemini users to prevent catastrophic harm.

Ideal candidate

A mission-driven engineer with deep curiosity for science and safety who thrives digging into anomalies, debating mass-casualty risks, and shipping reliable safeguards under tight timelines.

Requirements

  • Bachelor's degree or equivalent practical experience in a management, scientific, technical or engineering field
  • 8 years of experience writing code in a shared, version-controlled codebase with other contributors
  • 3 years of experience training, fine-tuning or evaluating machine learning models
  • Master's degree or PhD in Chemistry, Physics, Chemical or Nuclear Engineering, Biology, or Computational Science, or related field
  • Experience building classifiers or evaluation infrastructure for large language models
  • Experience applying statistics to machine learning evaluation
  • Experience running software in production, including monitoring, on-call or incident response
  • Experience in chemical, biological, radiological or nuclear security, export control, or adversarial work such as red teaming

Lab profile

About Google DeepMind

Google's AI lab building frontier models like Gemini to advance science and general intelligence.

What they build

  • Gemini
  • Gemma
  • AlphaFold

Known for

  • Frontier foundation models and GenAI
  • Large-scale training with JAX, PyTorch, TensorFlow
  • Model evaluation and deployment expertise
  • Responsible frontier AI research

Key facts

  • Founded in 2010
  • Headquartered in London, UK
  • Part of Google (Alphabet)
More about Google DeepMind →
Apply on the lab’s site ↗

Posted · Last seen