We're looking for a Security Researcher to define and defend against the emerging threat landscape of AI agents. This is a role for someone who thinks like an attacker but builds like an engineer – you'll discover vulnerabilities, design mitigations, and shape how enterprises secure their AI adoption.
What You'll Do
- •
Research AI agent attack vectors – understand how AI agents can be exploited, manipulated, or misused in enterprise environments.
- •
Discover and document vulnerabilities in AI agent architectures, authentication flows, and permission models.
- •
Design and build detection and prevention mechanisms for novel AI-specific threats.
- •
Develop security frameworks and best practices for AI agent deployment.
- •
Work closely with engineering to translate research into product capabilities.
- •
Publish research and represent Webrix in the security community – conferences, blogs, advisories.
- •
Stay ahead of the rapidly evolving AI security landscape and inform product strategy.
What We're Looking For
- •
3+ years in security research, offensive security, or threat intelligence.
- •
Deep understanding of application security fundamentals – authentication, authorization, injection attacks, and beyond.
- •
Familiarity with AI/ML systems – you don't need to be an ML engineer, but you understand how these systems work and fail.
- •
Experience with security tooling and automation – you build tools to find and fix problems at scale.
- •
Strong communication skills – you can explain complex vulnerabilities to both engineers and executives.
- •
Self-motivated researcher mindset – you dig until you find the answer.
- •
Bonus: Experience with LLM security, prompt injection, or AI safety research.
Why Webrix
You'll define security for the AI era.
AI adoption is accelerating faster than any technology shift before it. Soon, every employee will delegate thousands of tasks to AI agents – running in parallel, accessing sensitive data, performing actions across internal systems and SaaS tools. Today, this layer has zero governance.
Webrix is building the control layer for AI agents: zero-trust authentication, app-aware permissions, centralized audit trails. We enable adoption without compromising security. Every agent, every tool, one control plane.
We're already in production with forward thinking enterprises. The market is moving fast – and we're positioned to lead it.
What else:
- •
Founding impact: You're not joining a team – you're building it. Early equity, real ownership, direct influence on product and company direction.
- •
Ship to real customers: No theoretical exercises. Enterprises are using what we build today.
- •
Exceptional team: Small, senior, low-ego. Everyone here can build.
- •
The right moment: Strong traction, active fundraising, and a market that's exploding. This is the window.
