AI Security Researcher

Location: Tel Aviv, Israel

Company

hirify.global provides an AI-native security validation platform that helps enterprises discover, validate, prioritize, and remediate exploitable security exposures.

What you will do

• Conduct engineering-level application security reviews of architectures, code, and development processes.
• Lead AI-focused security assessments and red-team engagements for enterprise customers.
• Assess vulnerabilities in AI/ML systems, agentic workflows, and LLM-based applications.
• Enhance AppSec processes with agentic tools and AI security layers.
• Research attack techniques including prompt injection, model manipulation, and agentic framework exploits.
• Translate offensive findings into practical recommendations for customers and internal teams.

Requirements

• Deep hands-on application security experience at an engineering level, including code and architecture reviews with development teams.
• At least one year of dedicated experience in AI security research, experimentation, or offensive engagements targeting AI/ML systems.
• Strong offensive security capabilities focused on AI-specific attack vectors.
• Strong understanding of LLMs, agentic systems, and common AI application architectures.
• Ability to read and write code, build tools, and understand codebases.
• Fluent English and confidence working directly with enterprise customers.

Nice to have

• Published research or public talks on AI security.
• Traditional penetration testing or red-team experience.
• Experience building or deploying AI/ML systems.

Culture & Benefits

• Work in a growing cybersecurity company with more than 350 employees and customers in over 60 countries.
• Contribute to emerging AI security research and the development of AI threat knowledge.
• Collaborate with development teams and enterprise customers in hands-on technical engagements.
• Equal opportunity workplace committed to a diverse workforce.