Research Engineer/Scientist, AI Control jobs in United States
cer-icon
Apply on Employer Site
company-logo

Google DeepMind · 2 days ago

Research Engineer/Scientist, AI Control

Google DeepMind is a team of scientists and engineers advancing the state of the art in artificial intelligence. The role involves researching, designing, and building technology to control advanced AI systems, focusing on safety and ethical considerations.

Artificial Intelligence (AI)Business DevelopmentFoundational AIMachine Learning
check
Growth Opportunities

Responsibilities

Identify and formalize unsolved research problems in AI control, focusing on the unique challenges posed by agents that may exceed human oversight capabilities
Design, prototype, and evaluate novel control systems and monitoring techniques. This includes theoretical work, large-scale experiments, and building proof-of-concept systems
Collaborate closely with teams working on Gemini and agent infrastructure to understand emergent risks and integrate control mechanisms directly into the systems where they are most needed
Publish groundbreaking research and contribute to the broader academic and policy conversation on long-term AI safety and control

Qualification

AI safetyAI alignmentPh.D. in Computer ScienceSoftware engineeringML frameworksAdversarial researchGame theoryResearch impact

Required

Ph.D. in Computer Science or related quantitative field, or B.S./M.S. in Computer Science or related quantitative field with 5+ years of relevant experience
Demonstrated research or product expertise in AI safety, AI alignment, or a related security field

Preferred

Experience with adversarial research, red-teaming, or vulnerability research, particularly in complex software or AI/ML systems
Strong software engineering skills and experience with ML frameworks like JAX, PyTorch, or TensorFlow
Familiarity with concepts from game theory or mechanism design problems as they apply to AI
A track record of landing research impact within multi-team collaborative environments

Benefits

Bonus
Equity
Benefits

Company

Google DeepMind

company-logo
Google DeepMind aims to research and build safe artificial intelligence system to solve intelligence and advance science and humanity. It is a sub-organization of Google.

Funding

Current Stage
Late Stage
Total Funding
unknown
2014-01-26Acquired
2011-02-01Series A

Leadership Team

leader-logo
Demis Hassabis
Co-Founder & CEO
linkedin
leader-logo
Aaron Saunders
VP of Hardware Engineering, Robotics
linkedin
Company data provided by crunchbase