Offensive AI Security Researcher

Lex; Paris; Sur place; EUR 140 000 - 180 000; Plein temps

Résumé du poste

Apple’s Security Engineering & Architecture (SEAR) is tackling security across all Apple platforms. In this role you will identify and exploit vulnerabilities in AI-powered features and agentic systems, building offensive capabilities and anticipating how adversaries may exploit AI-enabled systems.

You will join world-class offensive security researchers to shape Apple’s security posture, conducting AI-specific attack research including prompt injection and data exfiltration.

Qualifications

• Solid grounding in vulnerability classes (memory corruption, logic flaws, auth bypass).
• Proven security research or offensive security experience across platforms.
• Strong knowledge of modern AI/LLM systems and failure modes.
• Experience applying AI/ML tools to security research workflows.
• Familiarity with agentic AI systems and prompt injection techniques.

Responsabilités

• Identify and exploit vulnerabilities in AI-powered features and agentic systems across Apple platforms.
• Build offensive capabilities against autonomous systems and anticipate exploits in AI workflows.
• Collaborate with world-class researchers to shape Apple's security posture.

Connaissances

Python

C/C++

Swift

Objective-C

AI/ML tools

Security research

Reverse engineering

Vulnerability discovery

Offensive security

Outils

IDA

Ghidra

LLDB

Description du poste

Apple’s Security Engineering & Architecture (SEAR) is tackling security across all Apple platforms. In this role you will identify and exploit vulnerabilities in AI-powered features and agentic systems, building offensive capabilities and anticipating how adversaries may exploit AI-enabled systems.

You will join world-class offensive security researchers to shape Apple’s security posture, conducting AI-specific attack research including prompt injection and data exfiltration.