Senior Security Researcher

As a Senior Security Researcher at Token Security, you will lead deep-dive research into AI products, LLM frameworks, and modern agentic AI ecosystems. You combine hands-on defensive and offensive research techniques with Token's platform to analyze modern AI products, dissect non-human identity architectures, and uncover privilege escalation paths in dynamic AI agent workflows. You bridge deep security research, product engineering, and technical storytelling, turning novel insights into real-world enforcement mechanisms, core platform capabilities, high-impact blogs, and talks at top global security conferences.

What you'll do

• Perform deep technical analysis on modern AI products, SaaS LLM offerings, and agentic tools to expose security gaps, privilege escalation risks, and data leakage vectors
• Research and prototype security enforcement models to protect, monitor, and govern autonomous AI Agents, enforcing token boundaries and runtime access controls
• Author technical blog posts, research papers, and vulnerability disclosures, and represent Token Security by submitting and presenting original research at top global security conferences such as Black Hat, DEF CON, and RSA
• Leverage AI Agents and modern AI tooling to scale research workflows, automate environment discovery, and accelerate vulnerability analysis across complex environments
• Conduct deep security research into active customer environments during key proof-of-concepts, identifying complex non-human identity and AI misconfigurations to build actionable, high-impact security reports
• Collaborate closely with Product, Engineering, and Sales to convert research findings into automated detections, platform features, and executive presentations

What you bring

• 5+ years of experience in security research, cloud security research, defensive or offensive security, or vulnerability research
• Practical experience or deep technical research into AI architectures, LLM execution pipelines, API security, and agentic execution environments
• Thorough understanding of organizational security, cloud environments, enterprise IAM models, enterprise AI platforms, and SaaS AI ecosystems such as OpenAI, Claude Enterprise, and Copilot
• Proven ability or strong desire to articulate complex research findings into engaging technical blogs, whitepapers, and public presentations for global security audiences
• Advanced proficiency in modern programming and scripting languages to write custom research tools, interact with APIs at scale, and build dynamic agent workflows
• Ability to analyze how enterprise AI products work end-to-end and invent novel, frictionless ways to enforce security policies without breaking user experience or usability
• Fluent English, written and verbal

Nice to have

• A track record of speaking at security conferences such as Black Hat, DEF CON, RSA, OWASP, or BSides
• Published security advisories, CVEs, or high-impact technical blog posts

What we offer

• Hybrid work model based in Tel Aviv, Israel with in-office presence and work from home on Tuesdays

About Token Security

Token Security is pioneering the AI Agent and non-human identity security space. The company combines research-driven innovation with thought leadership, using AI Agents to accelerate research workflows and delivering direct market and product impact through core platform enforcement capabilities and threat intelligence for global enterprise customers.