We are looking for a Principal AI Security Researcher with deep, hands-on expertise in AI red teaming and AI security to lead and scale RLGym’s AI security research efforts.
This is not a traditional cybersecurity leadership role. We need someone who has directly worked on breaking, attacking, testing, and securing AI systems, particularly large language models (LLMs), generative AI applications, and agentic AI systems.
The ideal candidate has significant practical experience designing and executing AI red-team programs, developing adversarial attacks, identifying AI-specific vulnerabilities, building automated red-teaming capabilities, and translating findings into effective guardrails and security protections.
עיקרי התפקיד
Lead and scale multidisciplinary teams focused on AI red teaming, adversarial testing, and AI security research.
Design and execute sophisticated attacks against LLMs, GenAI applications, and agentic AI systems.
Research attack techniques including prompt injection, jailbreaks, indirect prompt injection, tool abuse, agent manipulation, data leakage, model misuse, and adversarial behavior.
Build and evolve AI red-teaming engines and automated adversarial testing systems, including RLGym.
Building and scaling global AI security teams (red teaming, adversarial research, guardrails engineering) while fostering an innovation-driven security culture.
Overseeing advanced adversarial evaluations for GenAI models, agentic AI, and multi-agent (A2A) systems
Defining and implementing AI red-teaming frameworks aligned with OWASP AI Security guidelines, MITRE ATLAS, and NIST AI RMF, and operationalizing automated red-team engines to continuously stress-test models at scale.
Partnering with product and engineering to design and deploy enterprise-ready AI guardrails – including policy enforcement layers, monitoring pipelines, and anomaly detection systems – and championing secure deployment practices for GenAI (including agent orchestration via MCP and A2A workflows).
דרישות
What we need to see:
Extensive leadership experience managing and scaling security or R&D organizations, with a strong track record of building high-performance teams and driving complex projects to completion.
Deep expertise in cybersecurity and AI – proven understanding of AI threats, adversarial machine learning, LLM vulnerabilities, and AI safety frameworks (OWASP Top 10 for LLMs, NIST AI Risk Management Framework, etc.).
Strategic mindset and execution skills, with the ability to set vision and direction for AI security initiatives and also dive into technical details when needed.
Excellent communication and collaboration abilities, including experience working cross-functionally with product, engineering, and compliance teams, and conveying technical concepts to executive stakeholders.
5+ years of relevant industry experience in cybersecurity, machine learning security, or related fields (with a focus on enterprise-scale products and AI systems).
Ways to stand out from the crowd:
Demonstrated thought leadership in AI security – for example, publishing research, speaking at industry events (Black Hat, DEF CON, OWASP Global AppSec), or contributing to AI security standards and open-source projects.
Experience building or deploying AI security products and tools, such as red teaming automation platforms, guardrail frameworks, or AI monitoring and anomaly detection systems.
Hands-on familiarity with agentic AI frameworks and protocols (e.g. LangChain, AutoGen, MCP, A2A) and cloud-based AI environments, showing you understand how to secure complex AI orchestration workflows.
A background in AI trust and safety or adversarial ML research, with insight into emerging threats and mitigation techniques for GenAI applications.
About Alice
Alice is widely considered a global leader in online safety and AI security. We have some of the most forward-thinking and passionate minds in the world working to safeguard over 3 billion users across the largest AI and tech platforms. If you're creative and driven to secure the future of AI, we want to hear from you!