AI Security Architect

Do you have experience in AI Security with hands-on experience securing AI, Generative AI, LLM or agent-based environments?If so, this could be an opportunity worth considering.

This is a 6-month Inside IR35 contract role, offering a predominantly remote/hybrid working arrangement in London with a competitive day rate

An opportunity has arisen for an AI Security Architect to join a well-established health research organisation and charity supporting large-scale medical research to improve disease prevention, diagnosis and treatment.

You will design and implement security frameworks, controls and secure operating models that enable the safe deployment and use of AI solutions across complex business environments.

.

This role focuses on AI security assessments, threat modelling, governance frameworks, security controls, secure integrations and identifying AI-specific security risks.

Please only apply if you have the right to work in the UK, as visa sponsorship is not available.

You will be responsible for? Conducting security assessments of AI solutions, including threat modelling.


? Developing governance frameworks, security standards and best practice for AI adoption.


? Designing controls for identity, access management, auditability and human oversight.


? Supporting the implementation of security guardrails for AI, generative AI and agent-based systems.


? Defining secure integration patterns between AI platforms and enterprise systems.


? Identifying and mitigating AI-specific threats, including prompt injection, jailbreaks, data leakage, poisoning and model extraction/inversion.


? Collaborating with security, technology and business teams to balance innovation with security.


? Providing guidance and knowledge transfer on AI security principles and emerging risks.


? Producing clear documentation, standards and operational guidance.




If you have the required experience, applications are welcomed from candid