Principal AI Security Researcher

Opera•Singapore, Poland

About The Position

Join Opera's AI Hacker Team as a Principal AI Security Researcher. Opera is looking for a technically exceptional Principal AI Security Researcher to help shape the future of safe and secure agentic AI. As a senior member of Opera's AI Hacker team, you will define the research agenda, identify emerging risks across agentic AI systems, and help establish Opera as a respected voice in AI security. You will combine deep technical expertise with original research, working closely with engineering, product, and security teams to influence both internal product development and broader industry conversations. This is a unique opportunity to work at the forefront of AI security, exploring novel attack surfaces across AI-powered browsers, autonomous agents, multi-agent systems, and emerging AI technologies.

Requirements

Extensive experience in offensive security research, vulnerability discovery, or AI security
Demonstrated record of discovering and disclosing vulnerabilities, CVEs, offensive research, or impactful security findings
Deep understanding of AI systems, LLM applications, agentic frameworks, prompt injection, tool abuse, and adversarial AI techniques
Strong software engineering capabilities with the ability to develop research tooling, proof-of-concepts, and testing frameworks
Recognized presence within the security research community through conference talks, publications, open-source contributions, or industry leadership
Experience leading research initiatives and operating independently in highly ambiguous environments
Excellent written and verbal communication skills with the ability to explain complex security concepts to technical and non-technical audiences

Nice To Haves

Black Hat, DEF CON, OffensiveCon, TROOPERS, or equivalent conference speaking experience
Published AI security research or peer-reviewed academic work
Experience leading AI red teaming programs
Contributions to AI security tooling or standards initiatives

Responsibilities

Lead original security research focused on agentic AI systems, tool-using agents, multi-agent workflows, MCP-based architectures, and AI-powered browsers
Identify, validate, and demonstrate novel attack vectors and adversarial techniques against AI systems in controlled and authorized environments
Define Opera's long-term AI security research roadmap and identify emerging threats relevant to our products and users
Publish high-quality technical research, vulnerability disclosures, whitepapers, and conference presentations
Represent Opera at industry conferences, security events, and technical forums
Conduct security assessments, architecture reviews, and red team exercises for AI-powered products and services
Collaborate closely with product and engineering teams to translate research findings into secure product designs and engineering practices
Mentor and guide AI Security Researchers across the team
Contribute to open-source tooling, industry standards, and responsible disclosure initiatives