Technical AI Security Expert – Senior Associate / Manager

About the role

PwC's Cybersecurity team in Zurich is looking for a Senior Associate or Manager to join its Advisory practice and help strengthen the firm's ability to advise clients on the security of AI systems, including GenAI, LLM-based and agentic solutions. The role brings deeper technical AI Security experience to complement existing AI Security governance and risk work, and suits a client-facing advisor who can independently assess how AI solutions are designed and operated.

Key responsibilities

• Lead or deliver the technical component of AI Security assessments, reviewing design, data flows, trust boundaries, identities, permissions, interfaces, dependencies, logging, containment and human oversight.
• Develop and apply threat models and abuse cases, covering prompt injection, data exfiltration, insecure outputs, excessive agency, tool misuse, poisoning, model or API abuse and identity or permission failures.
• Translate technical weaknesses into security requirements, control recommendations and prioritised remediation actions, working with specialist engineers where implementation support is needed.
• Define the scope of technical testing and control validation, direct specialist activity, review evidence and challenge whether remediation is sufficient.
• Take end-to-end responsibility for AI Security workstreams, from scoping and project setup through delivery, client communication and quality of outputs.
• Work with AI Security governance and risk colleagues and mobilise Technology specialists and subject matter experts when deeper expertise is required.
• Contribute to AI Security services, methodologies, reusable assets, proposals and thought leadership, and support the development of colleagues.

Required profile

• Several years of relevant cybersecurity expertise and a recent, demonstrable track record applying it to AI environments.
• Degree in Computer Science, Cybersecurity, Information Security, Engineering or a related field, or equivalent professional experience.
• Fluent English; German and/or French is a strong advantage.
• Experience in professional services, regulated industries or complex multinational environments, and experience contributing to methodologies, propositions, reusable assets, training or thought leadership, is advantageous.

Required skills

• Direct experience with the security of AI systems (GenAI, LLM-based or agentic solutions) and leading technical AI Security assessments, threat models, solution-security reviews and control evaluations.
• Strong practical understanding of AI-specific threats and controls, able to distinguish material exposure from theoretical findings.
• Ability to apply threat-modelling or abuse-case techniques and to define and direct technical testing or control validation.
• Structured problem-solving, workshop leadership, writing and communication skills, able to explain complex AI Security issues to technical and senior stakeholders.
• A plus: certifications, recognised AI Security training, or exposure to frameworks such as NIST AI RMF, ISO 42001, OWASP guidance for LLM applications or MITRE ATLAS.