Junior AI Red Team Researcher

About Us

Zenity is the first and only holistic platform built to secure and govern AI Agents from buildtime to runtime. We help organizations defend against security threats, meet compliance, and drive business productivity.

Trusted by many of the world’s F500 companies, Zenity provides centralized visibility, vulnerability assessments, and governance by continuously scanning business-led development environments.

We recently raised a $125 million Series C, solidifying our position as a leader in the industry and enabling us to accelerate our mission to secure AI Agents everywhere.

About the Role

Zenity’s AI Red Team plays a central role in the company’s operations. Powering the research behind Zenity Labs, positioning the company as a security thought leader, and speaking at top tier conferences. 

We’re looking for a highly skilled Junior Offensive Security Researcher to find new attack vectors, from initial exploitation to impact in the emerging world of Agentic AI, LLMs, and their surrounding ecosystem.

This role is ideal for researchers who are passionate about breaking new ground in the growing world of AI and impacting the future landscape of Zenity products.

Responsibilities

• Research emerging agentic technologies and uncover new exploits, attack vectors and risks. From initial exploitation to impact.
• Build tooling, harnesses, and test frameworks to scale attack discovery and make research repeatable. And contribute to internal red team infrastructure.
• Investigate the surrounding ecosystem, not just the model. This includes: plugins, connectors, MCP servers, orchestration frameworks, and different types of infrastructure. Mapping how weaknesses in one component can develop into full compromise.
• Work with product and engineering to translate offensive findings into new defense capabilities.

• Prior Red Team or Vulnerability Research experience
• Strong coding and scripting skills in languages such as Python, JavaScript and bash
• Solid Cloud and Appsec experience
• Prior understanding and experience with AI related vulnerabilities. Including: direct and indirect prompt injections, jailbreaks and AI related reconnaissance.
• Curiosity, creativity, and a self-driven approach to research.
• Most importantly: the ability to learn quickly and adapt in a fast paced environment.