Senior Security Researcher (AI Security)

TL;DR

Senior Security Researcher (AI Security): Leading research into novel risks, vulnerabilities, and attack vectors within AI frameworks and services to define AI security risk. Focus on analyzing AI systems from an attacker's perspective, uncovering 0-day vulnerabilities, and translating findings into product capabilities and industry research.

Location: Hybrid in Tel Aviv, Israel

Company

hirify.global is a global Exposure Management company providing best-in-class cybersecurity solutions to organizations worldwide.

What you will do

• Conduct technical analysis of AI frameworks, services, and architectures to discover novel risks, vulnerabilities, and attack vectors.
• Define AI security risk by analyzing how exposure is created and exploited in AI systems and collaborate with engineering/product teams.
• Evaluate the risk of pre-trained models, vector databases, and orchestration frameworks (e.g., LangChain, LlamaIndex).
• Author blogs, whitepapers, and technical advisories; present original research at leading conferences.
• Analyze AI systems from an attacker's perspective to define trust boundaries, map attack techniques, and identify exploitable paths.
• Investigate and analyze AI infrastructures and services to find 0-day vulnerabilities, security holes, weaknesses, and design flaws.

Requirements

• 5+ years of experience in security research, vulnerability research, or offensive security.
• Familiarity with OWASP Top 10 for Large Language Model Applications (prompt injection, data poisoning, system prompt leakage).
• Ability to analyze complex systems from an attacker's perspective, identify weaknesses and exploit them.
• Strong understanding of AI systems, frameworks, and deployment patterns, with proven ability to exploit them.
• Proven track record of novel, complex security research in cloud security or application security, with published work.
• Strong communication skills, written and verbal.

Nice to have

• Experience discovering and disclosing vulnerabilities (CVEs, bug bounty, responsible disclosure).
• Experience analyzing systems for data leakage or unintended information exposure.
• Solid understanding of cloud platforms (AWS, Azure, GCP) and cloud security concepts.
• Experience tracking the evolving AI ecosystem and translating new developments into security research.

Culture & Benefits

• Work alongside experienced researchers and engineers who live and breathe security.
• Join a culture of belonging, respect, and excellence with support and resources for impactful work.
• Opportunity to define a new discipline in AI security.
• Committed to promoting Equal Employment Opportunity (EEO).