About the Role
We are seeking an exceptionally skilled Artificial Intelligence Security Engineer to lead the security design and governance of our AI/ML ecosystem across multi-cloud environments. This is not a traditional security engineering role — it requires a rare combination of deep cybersecurity expertise and applied machine learning security knowledge.
The successful candidate will shape the secure adoption of AI across sensitive domains, working closely with AI researchers, cloud architects, compliance officers, and product security teams.
Key Responsibilities
* Design, implement, and continuously evolve security controls for AI/ML pipelines spanning data ingestion, feature engineering, model training, deployment, inference, and monitoring.
* Architect secure multi-cloud AI platforms (AWS Sagemaker, GCP Vertex AI, Azure ML) with strong identity, encryption, and compliance frameworks.
* Proactively defend against adversarial ML attacks (model inversion, prompt injection, evasion, poisoning) by developing and operationalising advanced countermeasures.
* Lead threat modelling for AI-driven systems, integrating traditional cyber risks with novel AI-specific threat vectors.
* Ensure responsible and compliant AI usage by embedding privacy-preserving techniques (federated learning, differential privacy, homomorphic encryption).
* Establish automated security-as-code guardrails within MLOps/CI/CD pipelines, including red-teaming of ML models.
* Conduct AI-specific penetration testing and model robustness evaluations.
* Translate regulatory and ethical requirements (UK GDPR, EU AI Act, ISO/IEC 42001, NIST AI RMF) into operational security controls.
* Collaborate with data governance and risk teams to ensure traceability, explainability, and audit readiness of AI models.
* Lead research and innovation in emerging AI security trends, contributing to publications, open-source tools, or industry working groups.
Required Qualifications
* 8+ years in cybersecurity, with at least 3+ years in AI/ML security.
* Proven hands-on experience with AI/ML platforms across AWS, Azure, and GCP.
* Strong background in adversarial machine learning and defensive ML techniques.
* Proficiency in Python (PyTorch, TensorFlow, Scikit-learn) and experience with secure ML frameworks.
* Practical expertise with data security technologies (Cloud DLP, KMS, HSM, Confidential Computing).
* Experience embedding security into CI/CD and MLOps pipelines (Kubeflow, MLflow, Argo, GitOps).
* Knowledge of federated learning and privacy-preserving AI.
* Familiarity with regulatory and ethical frameworks (UK GDPR, EU AI Act, ISO 27001, NIST AI RMF, CIS benchmarks).
* Strong knowledge of network security, cloud IAM, encryption, and PKI.
Preferred Qualifications
* MSc/PhD in Artificial Intelligence, Cybersecurity, or related discipline.
* Research or published work in AI security, adversarial ML, or privacy-preserving ML.
* Certifications: CISSP or GCP/Azure/AWS Security Specialist.
* Experience in highly regulated industries (Finance, Healthcare, Government).
* Hands-on work with zero-trust architectures for AI applications.
* Knowledge of quantum-safe cryptography applied to AI workloads.
What We Offer
* Opportunity to work at the forefront of AI and cybersecurity.
* Collaborative environment with cross-functional teams of engineers, researchers, and security specialists.
* Competitive salary, benefits, and professional development opportunities.
* Flexibility with hybrid or remote work options.
Why This Role Is Unique
This is one of the first roles in the UK market that demands deep expertise at the intersection of AI and security. The ideal candidate will be equally comfortable reviewing ML model code, architecting secure multi-cloud AI platforms, and guiding compliance with the EU AI Act.
Job Type: Full-time
Pay: £35,000.00-£42,000.00 per year
Work Location: Hybrid remote in Bristol BS14 9HL