AI Security Engineer - Red Team

Summary

We are the Apple Services Engineering (ASE) Security Red Team. We focus on deep technical security review work of critical ASE services and infrastructure. These security reviews will be scoped and focused on review depth and quality. We are growing our team and looking an AI Security Engineer to lead deep reviews that identify meaningful security improvement opportunities. In this role, you will work closely with the AI platform teams, security engineering, InfoSec, privacy, SRE, detection, and design review teams to keep Apple's services and AI agents secure for our users. You will identify security weaknesses, validate and design detection mechanisms, and provide actionable recommendations to enhance our security posture. You will go beyond simple to find risks and identify obscure and complex risks within AI integrations and deployments. You will collaborate with AI architecture and engineering teams to continuously validate and improve our security controls and detection capabilities, with a strong focus on developing repeatable testing frameworks and metrics-driven security improvements. If you love diving into complex AI systems, and driving the security of that system over time, we want to talk to you!

Description

In this role, you will scope and lead focused security reviews on critical internet scale AI deployments that include the agents, MCPs, their platform and supporting infrastructure. You will learn services’ AI architecture and risk profile to build a scope for our AI deployments that enables a meaningful security review. You will ensure that scope focuses on the use and relevant risks of in use AI models, while maintaining the model itself as out of scope. You will use AI to expedite all stages of your work, while maintaining accountability for all outcomes. You will use your depth of knowledge to identify risks that go undetected by agentic tools and processes to reinforce and improve those processes.

Responsibilities

• Responsible for the enumerating risks, planning reviews, and executing those reviews to identify vulnerabilities and improvement opportunities
• A technical expert in uncommon and obscure risks within AI deployments and AI platforms
• A technical expert in complex business logic risks that require a depth of understanding of the agents, mcps, models, services and their architectures
• A technical expert in methodologies for security testing of AI Agents
• Ability to identify areas that are ripe for improvement and establish appropriate security goals
• Current on new security technologies, vulnerabilities, and methodologies
• Ability to develop proof of concept systems to automate security recommendations, vulnerability discovery, and process workflows
• Ability to effectively use AI within your workflows
• Ability to identify areas of security risk that require additional focus and review after AI has performed initial reviews
• Ability to contribute improvement opportunities to AI tool and process engineering teams

Minimum Qualifications

• 6+ years in an information security field or software engineering; 2 or more of those years conducting security reviews
• 1+ year reviewing AI deployments such as MCPs and Agents
• 2+ years of manually reviewing source code to assist in finding vulnerabilities
• Experience building or contributing to AI tools or AI security tools
• Ability to adapt quickly to prioritization shifts and investigate unfamiliar technologies
• Extensive infrastructure, cloud, and application security experience
• Experience communicating risk to engineering and leadership teams

Preferred Qualifications

• 8+ years in an information security field; 4 or more of those years conducting security reviews
• Bachelors degree in Computer Science / Engineering or a related, with emphasis in security related fields (or equivalent experience)
• Ability to reason about and influence software architecture for security
• Community contributions like public CVEs, bug bounty recognition, open source tools, blogs, talks etc.