Security Researcher

A successful global company in the Trust & Safety domain is developing an AI-powered SaaS platform aimed at cleaning the internet of harmful and abusive content. Their real-time, low-latency system detects and mitigates abusive behavior across the public internet, helping to protect both users and organizations. This includes tackling content such as fake news, antisemitism, hate speech, and abuse, all while supporting operations at massive scale.

The company has raised over $100M in funding, with a solid base of large, paying customers from inception and is no longer dependent on external investors.

Located in central Israel, near a train and light rail station, operating in a hybrid work model with 3 work-from-home days. The company employs over 300 people globally.

Key Responsibilities:

• Execute simulated cyber-attacks on GenAI models to expose vulnerabilities.
• Conduct security assessments on AI systems and infrastructure.
• Perform risk analysis and define mitigation strategies.
• Work cross-functionally to improve model resilience and security protocols.
• Research emerging threats, testing methods, and AI security trends.
• Document findings and report to leadership.
• Educate teams on AI security best practices.

Requirements:

• 5+ years in offensive cybersecurity (web/app/API security, ethical hacking).
• Strong knowledge of GenAI models (e.g., GPT, DALL·E) and AI vulnerabilities.
• Proficient in Python/JavaScript and familiar with AI/ML frameworks.
• Knowledge of AI security standards, compliance, and data privacy (e.g., GDPR).
• Excellent analytical and communication skills.
• Preferred: OSWE/OSCP/OSCE3/SEC542/SEC522 certifications.