Security Researcher

I’m hiring for a early-stage AI Security startup working on protecting the next generation of AI systems inside large organizations.

We’re looking for a Security Researcher focused on AI / LLMs to join a lean, high-impact team.

This is a hands-on role where you’ll explore real vulnerabilities in AI systems and help shape how companies secure their use of AI.

What you’ll do

• Research vulnerabilities in AI systems (LLMs, Agents, prompt injection, misuse scenarios)
• Break and test real AI tools and workflows
• Identify new attack vectors and turn them into real protections
• Work closely with engineers to bring research into production
• Stay constantly up to date with the fast-changing AI landscape

What I’m looking for

• Background in Security Research / Vulnerability Research
• Strong curiosity and a “breaker” mindset
• Hands-on experience with AI tools (LLMs, APIs, Agents)
• Deep technical understanding of systems
• Ability to work independently and move fast

Someone who actively experiments with new technologies

Nice to have

• Experience with prompt injection / AI exploitation
• Offensive security background

Why this role

• Small team with real ownership
• Early-stage environment
• Work on a fast-growing and evolving domain
• Direct impact from day one

If you naturally try to break every AI tool you touch – this is probably for you.