Teams at Alice (Formerly ActiveFence)

Leads end-to-end delivery, quality, scaling, and operational performance of RL Gym programs for strategic AI partners. Translates research and model-development needs into program requirements, workflows, metrics, and scalable processes. Partners with frontier-model teams, Sales, Product, Research, Delivery, and Operations to scope, launch, iterate, and expand programs. Builds feedback loops, quality standards, and the program management and operations function while managing capacity, timelines, cost, throughput, and partner satisfaction.

Creates and evaluates adversarial attacks against LLMs and AI systems, including prompt injection, jailbreaks, agent manipulation, and tool-use attacks. Develops scalable attack-generation systems, benchmarks, datasets, and regression tests; assesses attack quality and model vulnerabilities; and communicates findings to data science, security, and engineering teams to improve AI robustness.

Leads a team of fraud threat analysts conducting OSINT and WEBINT investigations across web, mobile, social media, forums, apps, and the dark web. Sets research priorities, oversees technical validation of abuse scenarios, builds investigative tooling and research environments, analyzes datasets and telemetry, applies OPSEC, and delivers actionable fraud intelligence and mitigation guidance to clients and stakeholders.