AI Security Engineer - Red Team (United States, Remote)

3+ years of experience in cybersecurity with focus on red teaming, penetration testing, or security assessments. Experience with web application and API penetration testing preferred. Deep understanding of LLM vulnerabilities including prompt injection, data poisoning, and jailbreaking techniques. Practical experience with threat modeling complex systems and architectures. Proficiency in developing automated tooling to enable and enhance testing capabilities. Proven track record of leading client-facing security assessment projects. Excellent technical writing skills. Strong presentation and communication skills. Experience building processes, documentation, and tooling for service delivery teams. Understanding of AI/ML model architectures, training processes, and deployment patterns. Familiarity with AI safety frameworks and alignment research. Knowledge of emerging AI attack surfaces including multimodal systems and AI agents.

Lead end-to-end AI red teaming security assessment engagements with enterprise customers. Collaborate with clients to scope projects and define testing requirements. Conduct comprehensive security assessments of AI systems. Author detailed security assessment reports with actionable findings. Present findings and recommendations to stakeholders. Build upon and improve established processes and playbooks. Develop frameworks for consistent service delivery. Automate tedious, repetitive tasks to enhance team effectiveness. Develop novel red teaming methodologies for emerging modalities. Stay ahead of the latest AI security threats. Translate research into practical testing approaches. Collaborate with research and product teams.