E

Ernst & Young

Provides consulting, assurance, and tax services

Senior AI Security Engineer

Security Engineering & Architecture +1Updated on Nov 14
Full-timeTaguig, Metro Manila, PhilippinesNo salary listedIn-person

About the Job

Requirements

  • Strong understanding of the end-to-end Generative AI application lifecycle and its security risks.
  • Practical knowledge of large language models, prompt design, Retrieval-Augmented Generation, embeddings, vector databases, data-ingestion pipelines, and guardrails.
  • Hands-on experience building, integrating, testing, or securing AI agents and tool-enabled workflows.
  • Understanding of agent planning, memory, tool execution, multi-agent workflows, and human-in-the-loop controls.
  • Knowledge of Model Context Protocol architecture, authorization, permissions, and security considerations.
  • Experience conducting application security assessments, threat modeling, and security testing or red teaming.
  • Familiarity with current OWASP guidance for Generative AI, large language models, and agentic applications.
  • Knowledge of secure application architecture, API security, identity and access management, secrets management, and data protection.
  • Strong hands-on Python scripting or development skills.
  • Experience working with APIs, SDKs, authentication, Git, and automated testing.
  • Ability to independently review, debug, test, and secure human-written and AI-generated code.
  • Experience with Azure AI Foundry, Azure OpenAI, or comparable enterprise AI platforms.
  • Working knowledge of relevant AI risk and governance frameworks, including ISO/IEC 42001, the NIST AI Risk Management Framework and its Generative AI Profile, and the EU AI Act, with the ability to translate applicable requirements into technical controls.
  • Strong written and verbal communication skills, including the ability to explain technical risks to business stakeholders.
  • Bachelor’s degree in Computer Science, Cybersecurity, Engineering, Information Technology, or a related discipline, or equivalent practical experience.
  • Five or more years of relevant experience in cybersecurity, application security, software engineering, cloud security, AI engineering, or related fields.
  • Demonstrated hands-on experience working with Generative AI or agentic AI solutions.
  • Strong analytical, problem-solving, documentation, and stakeholder-management skills.

Responsibilities

  • Review and threat-model large language model, Retrieval-Augmented Generation, agentic AI, and multi-agent architectures.
  • Identify security risks across models, prompts, data sources, vector databases, memory, tools, APIs, and Model Context Protocol integrations.
  • Design and validate security controls and guardrails for AI inputs, outputs, data access, tool execution, and autonomous actions.
  • Conduct AI security assessments and red-team testing for threats such as prompt injection, jailbreaks, sensitive-data disclosure, poisoning, excessive agency, unsafe tool use, and privilege abuse.
  • Assess the security of Model Context Protocol clients, servers, tools, resources, authorization, permissions, and third-party integrations.
  • Build automated security tests and evaluation harnesses for Generative AI and agentic AI applications.
  • Validate access controls, least-privilege implementation, human-approval mechanisms, secure secret handling, logging, and monitoring.
  • Integrate AI security testing into development and release processes.
  • Document security findings and provide clear, practical remediation recommendations.
  • Translate AI risk and governance requirements into appropriate technical controls.
  • Collaborate with engineering and security teams to embed security throughout the AI development lifecycle.
  • Stay current with emerging Generative AI threats, agentic AI attack techniques, Model Context Protocol security risks, and defensive practices.

Desired Qualifications

  • Experience developing AI security testing or evaluation frameworks.
  • Experience with Promptfoo, DeepEval, Ragas, LangSmith, MLflow, or similar tools.
  • Experience implementing or assessing AI security controls in regulated industries.
  • Experience supporting ISO/IEC 42001, AI impact assessments, or EU AI Act compliance activities.
  • Familiarity with Azure security, Azure DevOps, Docker, Kubernetes, or Azure Kubernetes Service.
  • Knowledge of model training, fine-tuning, adversarial machine learning, or AI supply-chain security.
  • Relevant professional training or certification in cybersecurity, cloud security, AI security, or AI governance.

About the Company

Ernst & Young

Provides consulting, assurance, and tax services

EY (Ernst & Young) is a global professional services firm that provides consulting, assurance, tax, and transaction advisory services across industries such as energy, healthcare, financial services, and real estate. Its work centers on helping clients solve critical business challenges by offering high-value advisory support in areas like supply chain, cybersecurity, sustainability, and digital transformation; revenue comes from fees for consulting, audit, and advisory services. What sets EY apart is its breadth of services across multiple disciplines, deep industry knowledge, and emphasis on thought leadership and research to inform clients’ strategic decisions. The firm aims to help organizations improve operational efficiency, navigate regulatory environments, and stay ahead of market trends by delivering practical, evidence-based guidance and execution support.

Company size
10,001+
Company stage
Not listed
Total funding
Not listed
Headquarters
Boston, MA
Founded
1991

Recently Posted Jobs

Explore more opportunities at Ernst & Young

See more jobs