Teams at Alice (Formerly ActiveFence)

Conduct adversarial security research against frontier generative AI models and agentic systems. Identify jailbreaks, prompt injections, guardrail bypasses, data-exfiltration paths, and tool misuse. Build attack tooling, adversarial datasets, taxonomies, and evaluation scenarios using Python and agent frameworks. Apply offensive security techniques to LLM systems, track emerging threats, communicate findings through reports and talks, and collaborate with red-teamers, data scientists, and engineers.

Build and manage intelligence infrastructure across web and mobile environments. Monitor social platforms, forums, blogs, applications, and darknet sources to identify malicious activity, bad actors, distribution methods, and emerging threats. Conduct OSINT investigations, generate actionable insights, improve operational processes, and develop new research methods and tools supporting online safety and security.

Builds, manages, and integrates intelligence infrastructure across web and mobile environments. Monitors social platforms, forums, blogs, applications, and darknet sources to identify malicious activity, threat actors, distribution methods, and emerging abuse patterns. The role gathers OSINT, develops investigative insights, improves operational processes, and researches new intelligence methods and tools to support online safety and cybersecurity teams.