AI Security Engineer

Norton Blake; Greater London; Vor Ort; GBP 150.000 - 180.000; Vollzeit

Zusammenfassung

Norton Blake is seeking an experienced AI Security Engineer to join a leading investment bank on a 6-month contract. You will design, assess and deploy secure AI and GenAI solutions across the organisation, advising on secure architecture, third-party risk and governance.

The role involves designing security guardrails for prompt injection, data exfiltration and model poisoning, and collaborating with Engineering, Legal, Risk and Compliance to embed secure AI practices across delivery teams.

Qualifikationen

• Experience assessing AI/ML systems from a security perspective.
• Knowledge of AI security frameworks (OWASP Top 10 for LLM Apps, NIST AI RMF, MITRE ATLAS).
• Experience auditing external AI vendors and APIs.
• Ability to design security guardrails for AI solutions including prompt injection and data leakage.

Aufgaben

• Analyse AI/ML systems and architectures from a security perspective.
• Conduct security assessments, threat modelling and risk reviews for internal AI solutions and external vendors.
• Design security guardrails to protect against prompts, data exfiltration and model poisoning.
• Assess third-party AI APIs, platforms and suppliers for proper security and data protection controls.
• Define secure patterns for AI API integrations, authentication, identity management and data-in-transit protection.
• Translate AI security risks into practical recommendations for stakeholders.
• Collaborate with Engineering, Architecture, Legal, Risk and Compliance to embed secure AI practices.
• Support alignment with AI security frameworks and governance standards.

Kenntnisse

AI security

Security architecture

Threat modelling

API security

OAuth

IAM

Tools

NeMo Guardrails

Llama Guard

Vertex AI

Azure OpenAI

Jobbeschreibung

AI Security Engineer

Contract: 6 months
Engagement: Inside IR35
Client: Leading Investment Bank
Rate: £650

We are seeking an experienced AI Security Engineer to join a leading investment bank on a high-profile contract engagement. You will play a key role in ensuring AI and GenAI solutions are designed, assessed and deployed securely across the organisation.
This is an opportunity to work at the forefront of AI security, advising on secure architecture, third-party risk and governance across enterprise AI platforms, APIs and vendor solutions.

Key responsibilities

• Analyse AI and machine learning systems, architectures and integrations from a security perspective.
• Conduct security assessments, threat modelling and risk reviews for internal AI solutions and external AI vendors.
• Design and recommend security guardrails to protect against prompt injection, data exfiltration, model poisoning and other AI-specific threats.
• Assess third-party AI APIs, platforms and suppliers, ensuring appropriate security, data protection and risk controls are in place.
• Define secure patterns for AI API integrations, authentication, identity management and data-in-transit protection.
• Translate complex AI security risks into clear, practical recommendations for technical and non-technical stakeholders.
• Work closely with Engineering, Architecture, Legal, Risk and Compliance teams to embed secure AI practices across delivery teams.
• Support alignment with relevant AI security frameworks, regulations and enterprise governance standards.

Essential experience

• Proven experience assessing AI/ML systems and architectures through a security lens.
• Strong knowledge of recognised AI security frameworks, such as OWASP Top 10 for LLM Applications, NIST AI RMF or MITRE ATLAS.
• Experience auditing, security-vetting and assessing the risk profile of external AI vendors and third-party AI APIs.
• Demonstrable experience designing security guardrails for AI solutions, including controls for prompt injection, data leakage and model poisoning.
• Strong understanding of API security, OAuth, IAM, authentication protocols and secure data-in-transit practices for AI workloads.
• At least five years of experience in security architecture, threat modelling and secure system design within an enterprise environment.
• Ability to communicate complex technical and AI security risks clearly to senior business stakeholders.

Desirable experience

• Hands-on implementation of AI guardrail frameworks, including NeMo Guardrails, Llama Guard or cloud-native security proxies.
• Experience securing AI workloads on Google Cloud Platform, including Vertex AI and Gemini API integrations.
• Experience securing Azure OpenAI Service, Microsoft Copilot Studio and associated Azure IAM and data governance controls.
• Familiarity with Anthropic's developer platform, Claude models and enterprise security controls for Anthropic API deployments.
• Knowledge of emerging AI regulations and standards, including the EU AI Act and ISO/IEC 42001.
• Previous experience working within financial services, banking or another highly regulated environment.