AI Red Team Researcher

Location: Tel Aviv, Israel

Company

hirify.global provides an AI agent security platform for enterprise-scale visibility, governance, detection, prevention, and response across SaaS, custom platforms, and end-user devices.

What you will do

• Research emerging agentic technologies and identify new exploits, attack vectors, and security risks from initial exploitation through impact.
• Build tooling, harnesses, and test frameworks to scale attack discovery and make research repeatable.
• Contribute to internal red team infrastructure.
• Investigate plugins, connectors, MCP servers, orchestration frameworks, and related infrastructure beyond the AI model itself.
• Map weaknesses across ecosystem components to understand paths to full compromise.
• Work with product and engineering teams to turn offensive findings into defense capabilities.

Requirements

• Prior red team or vulnerability research experience.
• Strong coding and scripting skills in Python, JavaScript, and Bash.
• Solid cloud security and application security experience.
• Understanding and practical experience with AI-related vulnerabilities, including direct and indirect prompt injection, jailbreaks, and AI reconnaissance.
• Curiosity, creativity, self-direction, and the ability to learn and adapt quickly.

Culture & Benefits

• Research contributes to hirify.global Labs and the company’s security research and thought leadership.
• Opportunity to work on emerging AI agent and LLM security challenges.
• Collaboration with product and engineering on new security capabilities.