AI Safety & Red Teaming Lead
About the Position
Alice is seeking an experienced, technically fluent AI Safety & Red Teaming Lead to oversee end-to-end delivery for a high-stakes Generative AI safety engagement in London. You will lead a specialized multidisciplinary pod of Child Safety Researchers, reverse engineers, and adversarial jailbreakers—bridging deep domain intelligence with highly technical exploit and evaluation methodologies. You will own program execution, approve adversarial testing designs, ensure strict operational security, and present key findings and strategic recommendations directly to client leadership.
Key Responsibilities
- End-to-End Delivery & Program Management: Own the full delivery lifecycle from scoping and methodology design through execution, quality assurance, and final reporting—ensuring milestones, SLAs, and safety benchmarks are consistently met.
- Multidisciplinary Team Leadership: Manage, mentor, and coordinate a 100% on-site team of Child Safety Subject Matter Experts (SMEs), reverse engineers, and AI jailbreakers, balancing workloads, prioritizing high-risk vectors, and fostering psychological safety and resilience.
- Methodology Review & Technical Approval: Review, challenge, and approve adversarial testing frameworks, red-teaming methodologies, exploit techniques, and automated evaluation pipelines across text, image, video, multimodal, text-to-3D, and physical AI systems.
- Client Stakeholder Management & Executive Reporting: Serve as the primary day-to-day and executive liaison with external stakeholders. Lead technical briefings, defend research methodologies, synthesize complex findings into executive-ready presentations, and align testing outputs with evolving client policy and product roadmaps.
- Operational Security & Wellbeing Governance: Enforce strict compliance within a secured, access-controlled environment while proactively managing team wellbeing, exposure rotation, and resilience protocols for staff handling graphic and distressing child safety material.
Requirements
Requirements
- Leadership & Delivery Experience: Minimum 7+ years of experience in Trust & Safety, AI Red Teaming, Threat Intelligence, or Offensive Security, including at least 3+ years directly managing multidisciplinary technical and investigative teams.
- End-to-End Program Ownership: Proven track record managing complex, high-stakes client or enterprise engagements from inception to final executive delivery under tight timelines.
- Child Safety & Online Harms Literacy: Strong understanding of online child exploitation (CSAE/CSAM), grooming dynamics, and adversarial evasion tactics, with the operational maturity to lead teams exposed to severe online harms.
- Technical & Adversarial Fluency: Deep working knowledge of Generative AI architectures, LLM/multimodal vulnerabilities, jailbreaking techniques, reverse engineering concepts, and automated evaluation tooling—sufficient to rigorously critique and approve methodologies designed by senior technical specialists.
- Executive Communication & Client Presence: Exceptional verbal and written communication skills in English, with extensive experience presenting technical findings, risk assessments, and policy recommendations directly to senior external stakeholders (such as Big Tech product, policy, and engineering leads).
- Workplace & Security Compliance: Ability to work full-time (5 days a week) on-site at our London office within a strictly secured, access-controlled environment.
- Content Resilience: Demonstrated psychological resilience and emotional maturity to oversee high-severity child safety investigations and support team wellbeing under continuous exposure to distressing material.
About Alice
THE CHALLENGES ALONG THE WAY
1. Being Both Strategist and Executioner
One of the hardest parts of this role is that you’re both the visionary and the builder; the one drawing the map and paving the road.
That means switching between high-level strategy and hands-on experimentation daily, and doing it while bringing others along with you. There’s no playbook for this kind of work. You’re paving an unpaved road, one small experiment at a time.
2. Balancing Security and Innovation
ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the world’s largest enterprises and tech platforms every day.
As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.