Misuse Red Team - Research Engineer/Research Scientist
We are seeking a Misuse Red Team Research Engineer/Research Scientist to investigate how advanced AI systems may be misused, manipulated, or adapted for harmful purposes. You will design and execute rigorous adversarial evaluations across a range of capabilities, including persuasion, cyber misuse, privacy, fraud, biological or chemical risk, and other emerging threat areas. Your work will help identify weaknesses before they can be exploited and inform practical improvements to model behaviour, safeguards, monitoring, and deployment decisions.
You will develop threat models, misuse scenarios, test plans, and evaluation methodologies; conduct experiments using language models, tools, agents, and multimodal systems; and analyse results to distinguish isolated failures from systematic vulnerabilities. Responsibilities include building prototypes and automated testing pipelines, creating high-quality datasets and benchmarks, collaborating with safety, security, policy, and engineering teams, and clearly documenting findings for both technical and non-technical audiences. You may also contribute to incident investigations, red-team exercises, risk assessments, and the development of mitigations and defensive evaluations. The role requires sound judgement when handling sensitive material and a strong commitment to responsible research.
We are looking for candidates with a degree or equivalent experience in computer science, machine learning, security, applied mathematics, cognitive science, or a related discipline. Experience researching adversarial behaviour, AI safety, cybersecurity, trust and safety, abuse prevention, or sociotechnical risks is highly desirable. You should be comfortable programming in Python or a similar language, working with APIs and data analysis tools, and translating open-ended questions into systematic experiments. Strong analytical, communication, and writing skills are essential, along with intellectual curiosity, creativity, and the ability to challenge assumptions constructively. Experience with large language models, autonomous agents, red teaming, threat intelligence, or responsible disclosure is advantageous. We welcome applicants from varied backgrounds who can demonstrate disciplined research practice and a thoughtful approach to high-impact technology risks.
Misuse Red Team - Research Engineer/Research Scientist
Other similar jobs
Popular job searches
Your next job
starts here.
JOB SPECIALISMS
LATEST JOBS
TOP SEARCHES
LOCATIONS
- Security Engineer
- Security Analyst
- Security Architect
- IT Security Manager
- Security Consultant
- SOC Analyst
- Identity Access Management IAM
- Cyber Security Consultant
- Cloud Security
- Application Security
- Incident Response
- Penetration Tester
LATEST JOBS
- Security Engineer (Contractor)
- Vice President, Field CISO Com...
- Microsoft 365 & Security Infra...
- Senior ICT Security Designer
- Data Protection Expert
- Data Protection Officer: Schoo...
- Data Protection Officer
- IT CONSULTANT (IT Management,...
- Technology and Cyber Employee...
- Cyber Security Consultant
- Cyber Security Consultant (Pen...
- Platform and Services Engineer...