Director of AI Security Research
About the Position
We are looking for a Director of AI Security Research to lead and scale RLGym’s AI security research efforts.
This role requires deep, hands-on experience in AI red teaming, LLM security, GenAI, and agentic AI, combined with the ability to build and lead research teams, define strategy, and turn security research into scalable products and protections.
What you'll be doing
- Lead and scale teams across AI security research, AI red teaming, adversarial research, and guardrails engineering.
- Define the AI security research strategy, roadmap, and priorities.
- Lead advanced adversarial testing of LLMs, GenAI applications, agents, and multi-agent systems.
- Research attack techniques including prompt injection, jailbreaks, tool abuse, data leakage, model misuse, and agent manipulation.
- Build and evolve automated AI red-teaming platforms, including RLGym.
- Define and operationalize frameworks aligned with OWASP AI Security, MITRE ATLAS, and NIST AI RMF.
- Partner with product and engineering teams to build guardrails, monitoring, detection, and secure AI deployment practices.
- Drive secure architectures for agentic AI, including MCP and A2A workflows.
- Represent the company through research, industry collaboration, publications, and thought leadership.
Requirements
What we need to see
- Proven experience leading and scaling AI security research, technical security, or R&D teams.
- Deep hands-on expertise in AI security, AI red teaming, adversarial ML, and LLM vulnerabilities.
- Experience building and running large-scale adversarial testing or AI security evaluation programs.
- Strong understanding of GenAI and agentic AI security risks.
- Ability to combine strategic leadership with deep technical execution.
- Strong communication and cross-functional collaboration with product, engineering, and executive teams.
- 8+ years of relevant experience in cybersecurity, AI/ML security, security research, or related fields.
Ways to stand out
- Published research or speaking experience at conferences such as Black Hat, DEF CON, or OWASP Global AppSec.
- Experience building AI security products, red-team automation platforms, guardrails, or AI monitoring systems.
- Hands-on experience with LangChain, AutoGen, MCP, A2A, and agentic AI architectures.
- Background in AI trust and safety, adversarial ML, or AI security research.
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.