AI Security Researcher

bout the Role

We are looking for a brilliant and proactive AI Security Researcher with a strong offensive mindset to join our core team. This is a unique opportunity to shape the security landscape of the rapidly evolving AI world. You will be responsible for breaking, analyzing, and ultimately securing cutting-edge AI systems, with a focus on Agentic AI, Web, and Cloud environments.

We are looking for someone who lives and breathes the "Attacker’s Perspective"-someone who can identify vulnerabilities before they are even documented and help us build the research methodology from the ground up.

What You’ll Do

• Offensive Research: Conduct deep-dive research into AI models, frameworks, and agentic workflows to identify novel vulnerabilities and attack vectors.
• Red Teaming: Perform hands-on penetration testing and red teaming exercises on AI-native applications and cloud infrastructures.
• Outbound Research: Document your findings through technical blogs, whitepapers, and vulnerability disclosures (CVEs).
• Thought Leadership: Represent the company at major security conferences (DEF CON, Black Hat, etc.) and contribute to the global AI security community.

What You Bring

• The Offensive DNA: Proven experience in Pentesting or Red Teaming. You know how to break systems and find the "unfindable."
• Technical Versatility: Strong background in Web Security and Cloud Security. While Low-Level/OS experience is a plus, our focus is on the application and cloud layers.
• AI Curiosity: Deep interest or hands-on experience in AI Security (LLM security, prompt injection, adversarial attacks) and exposure to Agentic AI ecosystems.
• Independence: You are a self-starter who doesn't need a roadmap. You thrive in "blue ocean" environments where you define the tasks.
• Proactive Learning: You stay ahead of the curve in the fast-shifting AI world, constantly tracking new research, papers, and tools.
• Communication Skills: Ability to translate complex technical research into clear, impactful content (blogs/presentations).

Preferred Qualifications

• Experience leading research initiatives or small teams.
• A track record of published research, bug bounties, or speaking engagements.
• Experience with Python and modern AI frameworks (LangChain, AutoGPT, etc.).