Security Researcher

A high-growth Israeli cybersecurity startup engineering advanced cloud security and governance platforms specifically designed for Non-Human Identities (NHI).

As modern enterprise ecosystems transition toward autonomous workflows and generative technologies, the company delivers critical visibility, posture management, and threat prevention across machine identities, service accounts, and API access layers.

The technical environment offers a cutting-edge research frontier, focusing on uncovering attack vectors, vulnerabilities, and identity privilege boundaries across autonomous AI agents, enterprise LLM execution pipelines, and foundational model integrations.

The office is located in Central Tel Aviv adjacent to the light rail line, operating on a hybrid model with one day working from home.

Role Description

• Serving as a Senior AI Security Researcher / Cloud Security Researcher, driving deep technical investigations into emerging threats, attack surfaces, and governance models surrounding autonomous AI agents and Non-Human Identities (NHI).
• Conducting rigorous vulnerability research, penetration testing, and security analysis across modern LLM execution pipelines, agentic runtimes, tool-calling mechanisms, and agent-facing APIs.
• Uncovering novel exploitation techniques, prompt injection vectors, authorization bypasses, and data exfiltration pathways in enterprise AI ecosystems (e.g., OpenAI Enterprise, Claude Enterprise, Microsoft Copilot, and custom multi-agent frameworks).
• Translating complex offensive and defensive research findings into actionable security primitives, detection algorithms, and automated posture rules within the core NHI security platform.
• Authoring high-impact threat research, security advisories, and technical reports on emerging Agentic AI vulnerabilities and machine identity risks.
• Collaborating closely with Product and Backend Engineering teams to embed threat models directly into product architecture.

Requirements-

• 5+ years of hands-on experience in Security Research, Cloud Security Research, Vulnerability Research, or Offensive/Defensive Cyber Security – Mandatory
• Demonstrated domain expertise in AI & Agentic Security: deep technical understanding of AI system architectures, LLM runtime pipelines, API security, and autonomous agent execution environments – Mandatory
• Deep comprehension of Enterprise Security, Cloud Environments (AWS / Azure / GCP), and Identity & Access Management (IAM / CIEM / PAM) models – Mandatory
• Proven familiarity with enterprise AI platforms and SaaS AI ecosystems (e.g., enterprise LLM endpoints, AI developer frameworks, Copilot integrations) – Mandatory
• Hands-on proficiency in scripting and reverse/security tooling (e.g., Python, network proxies, API security scanners) for automated testing and PoC exploit development – Mandatory
• Strong technical writing and presentation skills, with fluent, high-level English communication (both written and spoken) – Mandatory
• B.Sc. in Computer Science, Software Engineering, Cyber Security, or equivalent background from an elite IDF technological intelligence unit (e.g., 8200) – Advantage