AI Safety Research Engineer (CBNR) - Safeguards

Google LLC; Mountain View (CA); Hybrid; USD 174,000 - 252,000; Full time

Job summary

DeepMind is seeking a Research Engineer in Mountain View for its Chemical, Biological, and Nuclear AI Safety initiative. You will join a team that develops safeguards for frontier AI models, writes production code, and deploys safety solutions to billions of users.

The role emphasizes applied research over policy or pure research, with strict data management, tight release timelines, and an on-call rotation. You will work with biologists, chemists, and physicists to advance safe AI.

Qualifications

• Bachelor's degree in a Management, Scientific, Technical, or Engineering field, or equivalent practical experience.
• 5 years of experience writing code in a shared, version-controlled codebase with other contributors, which may include research software.
• 3 years of experience training, fine-tuning, or evaluating machine learning models.

Responsibilities

• Build safeguards and test them with red teaming and evaluation.
• Design, build and run evaluations for risk in frontier models, including agentic systems risk.
• Lead reliability of key systems, including safeguards and incident response.
• Partner with scientific experts to turn their judgment into datasets and automated graders, managing sensitive data under strict security controls.
• Communicate results, including uncertainty and negative findings, to technical staff and leadership.

Skills

Code in shared codebase

ML model training/evaluation

Education

Bachelor's degree in a Management, Scientific, Technical, or Engineering field

Job description

DeepMind is seeking a Research Engineer in Mountain View for its Chemical, Biological, and Nuclear AI Safety initiative. You will join a team that develops safeguards for frontier AI models, writes production code, and deploys safety solutions to billions of users.

The role emphasizes applied research over policy or pure research, with strict data management, tight release timelines, and an on-call rotation. You will work with biologists, chemists, and physicists to advance safe AI.