Offensive Security & Red Team

Engineers in this role execute offensive security assessments and red team operations across AI company infrastructure, applications, and—critically—AI-specific attack surfaces including prompt injection, model exfiltration, agent abuse, and tool-use exploitation. They combine hands-on penetration testing and adversarial simulation with custom tooling development, performing both rapid, targeted engagements and comprehensive open-scope operations that validate detection and response capabilities end-to-end. What sets this work apart is the focus on emerging AI risks: engineers assess production language models, agentic systems, and ML pipelines alongside traditional cloud, Kubernetes, and endpoint surfaces. They sit within the security function, partnering closely with defensive teams and product engineering to identify vulnerabilities early in design, then translate findings into actionable risk narratives that drive remediation and inform broader security strategy.