EYTC-CS-Cyber Architecture- OT and Engineering-Cloud Security-Senior
About this role
Your Key Responsibilities
- Lead AI red teaming execution including prompt injection, jailbreak and data exfiltration scenarios
- Perform AI threat modelling across model, data, and application layers
- Design and implement LLM guardrails and RAG security controls
- Conduct ML pipeline and model lifecycle security reviews
- Secure APIs and AI inference endpoints in cloud environments
- Support incident response for AI-specific threats and exploitation attempts
- Integrate security controls into AI/ML pipelines and DevSecOps workflows
- Collaborate with SOC teams for AI workload detection and monitoring use cases
Skills and Attributes for Success
- Strong understanding of ML/GenAI concepts (LLMs, embeddings, pipelines)
- Hands-on experience in application security, API security and cloud security
- Knowledge of AI attack surfaces (prompt, model, data layers)
- Adversarial mindset with ability to simulate real-world attack scenarios
- Understanding of OWASP Top 10 and LLM vulnerabilities
- Working knowledge of MITRE ATT&CK framework
To Qualify for the Role
- 3–6 years of experience in cybersecurity, application security or cloud security
- Hands-on exposure to AI/GenAI security concepts or implementations
- Experience in vulnerability assessment, red teaming or threat modelling
- Working knowledge of cloud platforms (Azure/AWS)
Ideally, You’ll Also Have
- Hands-on experience with AI security tools such as Garak, PyRIT, LLM Guard
- Exposure to adversarial ML tools (ART, Foolbox)
- Experience integrating security into MLOps/DevSecOps pipelines
- Certifications in cloud or security domains (AZ-500, CEH, etc.)
What We Look For
- A self-driven cybersecurity professional with strong technical depth in AI security and the ability to independently drive security testing and implementation for enterprise AI workloads.
What We Offer
- Opportunity to work on advanced AI security engagements, exposure to global clients, and continuous learning in AI-led cyber defence and adversarial testing methodologies.
EY | Building a better working world
EY exists to build a better working world, helping to create long-term value for clients, people and society and build trust in the capital markets.
Enabled by data and technology, diverse EY teams in over 150 countries provide trust through assurance and help clients grow, transform and operate.
Working across assurance, consulting, law, strategy, tax and transactions, EY teams ask better questions to find new answers for the complex issues facing our world today.
- Start applying with LinkedIn
- Apply Now Start
-
Please wait...
- Connect with us
- Our locations
- My EY
- Site map
- Legal and privacy
- Labor condition applications
- Cookie Consent Manager
-
Opens in a new tab.
-
Opens in a new tab.
-
Opens in a new tab.
-
Opens in a new tab.
-
Opens in a new tab.
EY refers to the global organization, and may refer to one or more, of the member firms of Ernst & Young Global Limited, each of which is a separate legal entity. Ernst & Young Global Limited, a UK company limited by guarantee, does not provide services to clients.
×Cookie Consent Manager
When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. Because we respect your right to privacy, you can choose not to allow some types of cookies. However, blocking some types of cookies may impact your experience of the site and the services we are able to offer.
Required Cookies
These cookies are required to use this website and can't be turned off.
Required Cookies Show More Details Required Cookies Provider Description Enabled SAP as service provider We use the following session cookies, which are all required to enable the website to function:- "route" is used for session stickiness
- "careerSiteCompanyId" is used to send the request to the correct data center
- "JSESSIONID" is placed on the visitor's device during the session so the server can identify the visitor
- "Load balancer cookie" (actual cookie name may vary) prevents a visitor from bouncing from one instance to another