Job Search

We are seeking a skilled AI Red Team Engineer to join our dynamic team on a remote basis, preferably located in or around Coventry. In this role, you will be responsible for simulating real-world attacks on AI systems to identify vulnerabilities and enhance the security posture of our technology. You will design and execute red teaming exercises, leveraging your expertise in adversarial machine learning, penetration testing, and security assessments. Your analytical skills will be pivotal in developing strategies to exploit weaknesses in AI models and systems, providing actionable insights to improve defenses.

Key responsibilities include collaborating with cross-functional teams to understand the AI systems' architecture and design, identifying potential attack vectors, and developing custom tools for testing. You will also be tasked with documenting findings, creating detailed reports, and presenting your recommendations to stakeholders. A solid understanding of ethical hacking principles, machine learning frameworks, and AI security best practices is essential. Ideal candidates will have a background in cybersecurity, experience with programming languages such as Python, and familiarity with relevant tools and methodologies in the red teaming domain.

To be successful in this position, you should possess strong problem-solving skills, the ability to think critically and creatively, and a passion for staying updated on emerging threats and technologies in AI security. If you are driven, innovative, and ready to tackle the challenges of securing AI systems, we would love to hear from you.