AI Security Researcher (Cybersecurity)

TL;DR

AI Security Researcher (Cybersecurity): Investigating the intersection of adversarial tradecraft and generative AI systems to build defensive capabilities for an AI observability platform with an accent on LLM misuse, autonomous agents, and multi-modal AI. Focus on discovering new attack vectors like jailbreaking and adversarial prompting and translating these findings into product features.

Location: Remote (Israel)

Company

hirify.global is building an endpoint AI observability platform to maximize the productivity and safety of AI adoption in organizations.

What you will do

• Research how adversaries exploit generative AI tools, including LLMs and autonomous agents.
• Conduct hands-on experiments with adversarial prompting and jailbreak methods.
• Implement research findings as actionable improvements for the product.
• Create public-facing security content, such as blog posts and conference talks.
• Act as a subject matter expert in adversary tradecraft for various business units.

Requirements

• 2+ years of experience in offensive (red team/purple team) or defensive security research.
• Ability to develop research tooling through code.
• Strong communication skills to explain complex technical concepts to executive and technical audiences.
• Must be based in Israel

Nice to have

• Experience with prompt engineering, model exploitation, or agentic misuse.
• Knowledge of reinforcement learning or model interpretability.
• Proficiency in Rust or C/C++.
• Knowledge of OS internals and reverse engineering.

Culture & Benefits

• Distributed team culture based on trust, autonomy, and excellence.
• Generous healthcare and home-office support.
• Flexible PTO.