Security Researcher

A successful global company developing AI-driven technology aimed at making the internet safer by reducing harmful and abusive content.

With hundreds of employees, the company is based in Ramat Gan, close to both light rail and train lines, and offers a flexible hybrid work model.

Role overview

• Conduct research-focused work on AI and LLM models, rather than traditional websites or applications.
• Analyze and probe the behavior of generative AI models (e.g., ChatGPT-like systems).
• Explore and identify ways to bypass or stress-test model safety and guardrails.
• Apply curiosity-driven research, creative thinking, and experimentation.
• Contribute insights that help improve AI safety, robustness, and content moderation.

Requirements

• 3 years of experience as a Security Researcher.
• B.Sc. or M.Sc. in Computer Science, Cybersecurity, or a related field or equivalent experience from an elite technological military unit.
• 3+ years of offensive security experience, with a focus on web and API security, vulnerability assessment, and ethical hacking.
• Deep understanding of AI technologies, including generative models (e.g., GPT, DALL·E).
• Familiarity with AI security frameworks, compliance standards, and ethical guidelines.
• Strong proficiency in Python, JavaScript, and additional languages relevant to AI and cybersecurity.