Security Researcher

Join Onyx Security and help build the control plane for autonomous AI in a fast-moving, high-impact environment. Onyx is building the control layer that enables enterprises to safely adopt and scale AI agents across the organization, with the visibility, governance, and operational control needed to understand what agents exist, what they do, how they behave, and what risks they introduce.

About the role

Onyx is looking for a hands-on Security Researcher to help build the next generation of AI security capabilities. In this role, you will research emerging attack techniques, AI and cloud risks, and detection approaches, then translate that research into product-grade capabilities.

What you will do

• Research vulnerabilities, attack paths, and abuse patterns in AI and cloud-native environments.
• Design detections, prevention logic, and security capabilities based on findings.
• Develop code and prototypes that can be integrated into the product.
• Collaborate with engineering and product on new security features.
• Monitor the threat landscape and contribute insights internally and externally.

What you will bring

• 5+ years of experience in security research, vulnerability analysis, or related fields.
• Strong coding skills in Python, Go, Rust, C/C++, or similar.
• Deep understanding of systems, operating systems, and security fundamentals.
• Experience with cloud infrastructure, containers, and modern attack techniques.
• Strong communication skills and research-driven mindset.

Nice to Have

• Background in offensive security, red teaming, or detection engineering.
• Publications, talks, or CVEs.
• Experience in runtime, cloud, or AI security domains.