Job Description

Position Overview

The Offensive Security Research Team seeks a Cyber Security Researcher to perform AI-focused red team testing and vulnerability analysis. This role involves testing new AI offerings and integrations, building proof-of-concept exploits, and strengthening overall AI security posture through advanced offensive research.

Core Responsibilities

Conduct AI Red Team and penetration testing on LLMs, agentic systems, and AI-integrated applications.

Perform reverse engineering, create exploits, and simulate real-world attack vectors.

Identify, document, and mitigate vulnerabilities in AI models and supporting infrastructure.

Write technical reports detailing findings, attack chains, and security implications.

Collaborate with cross-functional teams to promote responsible AI deployment and secure engineering practices.

Required Skills & Experience

Skill Requirement

AI Cybersecurity Research 2+ years

Red Team / Pen Testing 2+ years

Exploit Development / Reverse Engineering 2+ years

AI Technologies (LLMs, Copilot, Gemini, MCP, Agentic Solutions) Hands-on

Information Security Engineering 4+ years

Technical Writing & Presentations 3+ years

Communication Skills Strong verbal & written

Additional Notes

Must have direct experience testing AI systems (LLMs, Copilot, Gemini, etc.).

Military or equivalent cybersecurity experience acceptable.

Collaborates directly with internal technology leadership on AI security best practices.

Job Tags

Similar Jobs