AGI Safety & Alignment Research Engineer

Socket.dev; San Francisco (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind is seeking researchers embedded as software engineers to drive large-scale alignment and safety experiments. You will design and run experiments, prototype architectures, and collaborate with academic partners to publish findings while applying advances to real-world AI systems.

The role emphasizes bridging research and product teams, contributing to interpretability, safety, and robust AI deployment across diverse projects.

Qualifications

• Bachelor's degree in Computer Science, a related Software Engineering field, or equivalent practical experience.
• 3 years of experience in software development, ML engineering, or ML research.
• Experience working with research teams.

Responsibilities

• Research new alignment methods and study their effectiveness.
• Develop adversarially robust AGI control systems and deploy them in production.
• Research interpretability techniques to understand what AI systems are thinking.
• Work with product teams to ensure that research is correctly adopted.

Skills

3 years of software development / ML

Research collaboration experience

Education

Bachelor's in CS / related field or equivalent

Job description

Google DeepMind is seeking researchers embedded as software engineers to drive large-scale alignment and safety experiments. You will design and run experiments, prototype architectures, and collaborate with academic partners to publish findings while applying advances to real-world AI systems.

The role emphasizes bridging research and product teams, contributing to interpretability, safety, and robust AI deployment across diverse projects.