GenAI Security Engineer: Threat Modeling & Red Team Lead

EY; Taguig; On-site; PHP 1,000,000 - 2,000,000; Full time

Job summary

EY is seeking a Senior AI Security Engineer to assess and strengthen secure GenAI and agentic AI deployments. You will model threats, test defenses, and collaborate with AI engineering, security, cloud, privacy, and governance teams to ensure secure, compliant solutions.

The role emphasizes hands-on work with LLMs, RAG, MCP integrations, and security automation within a enterprise GenAI program at EY.

Qualifications

• Strong end-to-end GenAI security risk understanding.
• Hands-on with LLMs, embeddings, vector databases.
• Experience with Azure AI Foundry or Azure OpenAI.
• Familiar with ISO/IEC 42001, NIST AI RMF, EU AI Act.
• Ability to translate risks into technical controls.

Responsibilities

• Review and threat-model LLM, RAG, agentic AI architectures.
• Identify security risks across models, prompts, data sources, and tools.
• Design and validate security controls and guardrails for AI inputs/outputs.

Skills

GenAI security

Threat modeling

Red-team testing

AI governance

API security

Cloud security

Education

Bachelor’s degree in Computer Science or related

Tools

Promptfoo

DeepEval

Ragas

LangSmith

MLflow

Job description

EY is seeking a Senior AI Security Engineer to assess and strengthen secure GenAI and agentic AI deployments. You will model threats, test defenses, and collaborate with AI engineering, security, cloud, privacy, and governance teams to ensure secure, compliant solutions.

The role emphasizes hands-on work with LLMs, RAG, MCP integrations, and security automation within a enterprise GenAI program at EY.