Search
Go
Misuse Red Team - Research Engineer/Research Scientist
Summary by AIEngineer.careers
Misuse Red Team - Research Engineer/Research Scientist is a AI Security Engineer role (full-time). with AI Security Institute. in GREATER LONDON, GB. Compensation shown: $80K–$179K (est.). Imported listing (source: jobs-radar.com). Apply on the employer's site (jobs-radar.com).
Imported listing (source: jobs-radar.com) · Apply on jobs-radar.com
GREATER LONDON · GB
$80K–$179K (est.)
Full-time
SENIOR
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from jobs-radar.com
Join the AI Security Institute to conduct red-teaming research on frontier AI models, identifying misuse vectors and dangerous capabilities. You will develop advanced automated attack tooling and share critical security findings with leading AI companies and government officials.
Responsibilities
- Red-team frontier AI safeguards for dangerous capabilities
- Research novel attack vectors against AI systems
- Develop advanced automated attack tooling
- Share findings with frontier AI companies and government officials
Requirements
- Strong background in AI security or adversarial machine learning
- Experience with red-teaming or penetration testing methodologies
- Ability to develop automated tooling for security research
Nice to Have
- Publications in AI safety or security conferences
- Experience working with government or policy bodies
Tech Stack
Adversarial TestingAI Safety
AI Security Institute
Greater London · GB · 208+ employees
The UK AI Security Institute is a research organisation within the Department for Science, Innovation and Technology focused on understanding advanced AI risks and developing safety and security mitigations. It evaluates leading AI systems, conducts research, collaborates with industry and governments, and supports policymakers.
