GenAI Safety Oversight Research Scientist

DeepMind Technologies Limited; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

DeepMind Technologies Limited is seeking experts for Safety Oversight to turn production data into intelligence about the safety of deployed AI models. The team will monitor model safety, alignment, and rapid mitigation of issues in production, collaborating with Gemini/GenMedia researchers.

Ideal candidates will have PhD/advanced degrees in CS or engineering, strong experience with large-scale data, and a track record of delivering scalable AI safety solutions that benefit users globally.

Qualifications

• PhD in Computer Science, a related field, or equivalent practical experience.
• Experience in the domain area of generative AI and Large Language Models (LLM).
• Experience building and shipping technical products.

Responsibilities

• Build classifiers and data pipelines to detect model misbehavior and misuse end-to-end.
• Research and develop cross-context monitoring systems to detect coordinated harms, developing novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors.
• Think critically about novel methods for monitoring using model activations, actions, chains-of-thought and final answers.
• Collaborate closely with infrastructure teams and data scientists to scale your work and regularly share results with the wider safety team.

Skills

Generative AI

Large Language Models

Experimentation collaboration

Data pipelines

Analytical thinking

Education

PhD in Computer Science

Master’s degree or PhD in Engineering/CS or related field

Job description

DeepMind Technologies Limited is seeking experts for Safety Oversight to turn production data into intelligence about the safety of deployed AI models. The team will monitor model safety, alignment, and rapid mitigation of issues in production, collaborating with Gemini/GenMedia researchers.

Ideal candidates will have PhD/advanced degrees in CS or engineering, strong experience with large-scale data, and a track record of delivering scalable AI safety solutions that benefit users globally.