AI Security Trainer

We are seeking a forward thinking and technically proficient AI Security Trainer to join our advanced training division. In this role, you will be responsible for developing and delivering innovative cybersecurity training programs focused on Artificial Intelligence, Machine Learning models, and Large Language Models (LLMs).

The ideal candidate sits at the intersection of traditional cybersecurity and data science, bringing practical experience in securing AI systems and a passion for education. Candidate will focus on creating engaging, hands-on learning experiences that equip professionals to defend against emerging AI-specific threats such as prompt injection, data poisoning, and model extraction. While formal education is valued, we prioritise proven technical competence with AI frameworks, adversarial testing, and the ability to translate complex AI safety concepts into actionable knowledge for diverse technical audiences.

Candidate will conduct dynamic training sessions for versatile level of audience using in-person, virtual, and hybrid formats. A core part of this role involves customizing training content to align with the specific needs of participants, ranging from secure MLOps pipeline development to LLM application security. Candidate will facilitate hands-on labs where students actively exploit and defend AI systems in safe, simulated environments.

You will design, develop, and continuously update specialized training materials, documentation, and interactive lab exercises. This includes creating engaging modules based on current frameworks like the OWASP Top 10 for LLM Applications and MITRE ATLAS. You will continuously monitor the rapidly evolving AI threat landscape to ensure all instructional content reflects the latest attack vectors, defensive strategies, and regulatory requirements.

Candidate will develop practical, scenario-based assessments such as AI red teaming exercises or CTF-style challenges to evaluate participant learning outcomes. By actively collecting and analysing feedback, candidate will continuously refine instructional methods and materials. Candidate will serve as an internal subject matter expert, supporting organizational AI governance and safety initiatives.

We require a minimum of 3 to 5 years of hands-on experience in cybersecurity, application security, or machine learning engineering, with at least 1 to 2 years specifically focused on AI/ML system security or AI safety. Additionally, candidates should have experience in a training, mentoring, or instructional role, proving the ability to effectively educate adult learners on complex, emerging technologies.

A bachelor's degree in computer science, Cybersecurity, Data Science, or a related field is preferred. However, we strongly value practical experience and will consider candidates with an equivalent combination of professional experience in securing AI applications and relevant industry certifications in lieu of a formal degree.

Candidates must prove a solid understanding of both traditional cybersecurity principles and the unique threat landscape of AI systems. Ability in Python and familiarity with AI/ML frameworks (such as PyTorch or TensorFlow) is required. Candidate must understand AI-specific attack vectors (prompt injection, jailbreaking, data poisoning) and defense mechanisms. Excellent verbal and written communication skills are essential, particularly the ability to bridge the communication gap between security teams and data scientists.

This position is based at our Head Office but supports a flexible, dynamic work environment. Occasional travel across the country may be required for project execution, on-site client training delivery, and coordination with geographically distributed teams.