Principal AI Security Researcher

About the role

Opera is seeking a technically exceptional Principal AI Security Researcher to shape the future of safe and secure agentic AI. As a senior member of the Security Team, you will define the research agenda, identify emerging risks, and position Opera as a leading voice in AI security.

Key responsibilities

• Lead original security research on agentic AI systems, tool‑using agents, multi‑agent workflows, and AI‑powered browsers.
• Identify, validate, and demonstrate novel attack vectors and adversarial techniques in authorized environments.
• Define Opera’s long‑term AI security research roadmap and publish high‑quality technical papers, vulnerability disclosures, and conference presentations.
• Conduct security assessments, architecture reviews, and red‑team exercises for AI‑powered products.
• Collaborate with product and engineering teams to translate findings into secure designs.
• Mentor AI Security Researchers and contribute to open‑source tooling and industry standards.

Required profile

• Extensive experience in offensive security research, vulnerability discovery, or AI security.
• Proven record of publishing security research, CVEs, or impactful findings.
• Strong presence in the security research community (talks, publications, open‑source contributions).
• Ability to operate independently in ambiguous, high‑impact environments.
• Excellent written and verbal communication skills for both technical and non‑technical audiences.

Required skills

• Offensive security research
• Vulnerability discovery
• AI security
• Large language model (LLM) applications
• Agentic AI frameworks
• Prompt injection techniques
• Tool abuse and adversarial AI techniques
• Software engineering for research tooling and proof‑of‑concepts
• Testing frameworks and red‑team methodologies