SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Spectrum Labs (operating as Alice) is seeking a Principal AI Security Researcher to lead and scale their AI security research organization, with a focus on red teaming, adversarial testing, and securing large language models and agentic AI systems.
In this role, you will lead multidisciplinary teams focused on AI red teaming and adversarial research. You'll design and execute sophisticated attacks against LLMs, generative AI applications, and agentic AI systems, researching attack techniques including prompt injection, jailbreaks, indirect prompt injection, tool abuse, agent manipulation, data leakage, and model misuse. You'll build and evolve AI red-teaming engines and automated adversarial testing systems, including RLGym, while scaling global AI security teams and fostering an innovation-driven security culture.
Key responsibilities include overseeing advanced adversarial evaluations for GenAI models and multi-agent systems; defining and implementing AI red-teaming frameworks aligned with OWASP AI Security guidelines, MITRE ATLAS, and NIST AI RMF; operationalizing automated red-team engines to continuously stress-test models at scale; and partnering with product and engineering teams to design and deploy enterprise-ready AI guardrails, including policy enforcement layers, monitoring pipelines, and anomaly detection systems.
You'll champion secure deployment practices for GenAI, including agent orchestration via MCP and A2A workflows. This is a strategic leadership role requiring both vision-setting and hands-on technical depth.
Required qualifications: 5+ years of relevant industry experience in cybersecurity, machine learning security, or related fields with focus on enterprise-scale products and AI systems. Extensive leadership experience managing and scaling security or R&D organizations with a track record of building high-performance teams. Deep expertise in cybersecurity and AI, including proven understanding of AI threats, adversarial machine learning, LLM vulnerabilities, and AI safety frameworks. Strategic mindset with ability to set vision and direction while diving into technical details. Excellent cross-functional communication and collaboration skills.
Standout qualifications include demonstrated thought leadership in AI security (publications, speaking at major conferences, contributions to standards), experience building AI security products and tools, hands-on familiarity with agentic AI frameworks (LangChain, AutoGen, MCP), and background in AI trust and safety or adversarial ML research.
