Research Engineer, AGI Safety and Alignment, DeepMind
Research Engineer, AGI Safety and Alignment, DeepMind Overview
| Company Name | |
| Job Role | Research Engineer, AGI Safety and Alignment, DeepMind |
| Qualifications | Bachelor’s |
| Category | IT Jobs |
| Job Type | Full Time |
| Location | London |
The Artificial General Intelligence (AGI) Safety and Alignment Team (ASAT) at DeepMind is dedicated to minimizing existential and catastrophic risks associated with AGI and future Artificial Superintelligence (ASI). The team focuses on researching innovative techniques and collaborating with other teams at Google to implement these strategies effectively. ASAT advises executive leadership on safety concerns and consists of specialized sub-teams that work on aligning future AI models, preparing for potential AGI risks, and developing tools to enhance safety research.
Responsibilities
- Conduct research on new alignment methodologies and analyze alignment failures while applying AGI-scalable alignment techniques to advanced models.
- Design and implement adversarially robust AGI control systems in production environments.
- Explore interpretability techniques to gain insights into the cognitive processes of AI systems.
- Collaborate with product teams to ensure the effective integration of research findings into practical applications.
Requirements
- A Bachelor’s degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience.
- At least 3 years of experience in software development, machine learning engineering, or machine learning research.
- Demonstrated experience working within research teams.
Benefits
- Opportunity to work in a pioneering AI lab focused on solving complex global challenges.
- Access to diverse learning opportunities and various career pathways.
- Engagement in a culture that prioritizes safety and ethics in AI development.
Degree Requirement: Bachelor’s
Visa Sponsorship Promising
To apply for this job please visit www.google.com.