Lead AI Red Team Specialist (Cybersecurity, Remote)

Job summary

An experienced red team specialist is sought to enhance a product and research team focused on evaluating vulnerabilities in large language models (LLMs). The role involves collaboration with experts across various digital disciplines to develop a testing tool for agentic workloads.

Qualifications

• Minimum of five years of experience in enterprise red teaming or offensive research.
• Proven expertise in web application pentesting with a focus on remediation.
• Experience in defining product roadmaps for red team tools is valued but not mandatory.
• Ability to assess complex technology stacks, including cloud platforms and AI systems.
• Strong communication skills for conveying technical findings to non-technical stakeholders.

Responsibilities

• Develop and innovate product modules related to application context testing, including API security and server-side vulnerabilities.
• Collaborate with a diverse team of researchers and developers to drive innovation in red team products.
• Conduct research on agentic vulnerabilities and stay updated on developments in the red teaming domain.

Skills

• Familiarity with Mitre and OWASP frameworks for client reporting.
• Relevant security certifications (e.g., OSCP, OSCE) are advantageous.
• Experience with agent-specific attack types like prompt injection and memory poisoning.
• Understanding of Model Context Protocol (MCP) and LLM pipelines.

Education

• Relevant educational background in cybersecurity or related fields is preferred but not explicitly required.

Tools

• Experience with open source and proprietary tools for web and application pentesting is essential. Familiarity with cloud platforms such as M365, Google Cloud, or AWS is also important.