This role requires a blend of deep research, secure systems design, and hands-on prototyping. You will pioneer new approaches to secure the AI development lifecycle, create systems that govern how agents interact safely with tools and APIs, and build solutions that bake security into the fabric of our agentic platforms. Your work will be crucial in shaping our long-term AI security roadmap and establishing new industry standards.
Design and build defenses that secure our Agentic AI ecosystem, our LLMs, and our cutting edge AI models.
Proactively identify and mitigate risks in this emerging domain by creating foundational security solutions.
Focus on developing scalable, secure-by-design frameworks that empower developers to build trustworthy applications.
Continuously drive and implement cutting-edge research and standards in agentic identity, authorization, and permissioning while converting those insights into production-grade controls and services deployed across the platform.
Requirements: To succeed in this role, youll need:
A Masters degree or PhD in Computer Science, or a related technical field, with a specialisation in Security or AI/ML.
7 years of experience with security assessments, design reviews or threat modelling.
7 years of experience in security engineering, computer and network security and security protocols.
7 years of programming experience in Java or Python,
Hands-on experience with agentic AI frameworks (e.g., LangChain, LangGraph).
Familiarity with authentication/authorization protocols (e.g., OAuth 2.0, OIDC, PKCE, API Keys) and agentic protocols (e.g. MCP, A2A)
A proactive and collaborative mindset, with a passion for continuous learning and a drive to solve complex challenges as part of a team.
(Bonus) Expertise in AI/ML security, including model and infrastructure vulnerabilities and their mitigation strategies.
(Strong Bonus) Deep understanding of Large Language Models (LLMs), Multimodal Language Models (MLLMs), and agentic workflows.
(Strong Bonus) Experience developing or evaluating security controls for agentic AI systems, including identity and consent models for multi-party protocols (e.g., MCP, A2A).
(Strong Bonus) Proficiency in implementing secure communication protocols for agent-to-agent interactions, such as OAuth 2.0, API keys, and PKCE.
(Bonus) A track record of contributions to the security and AI/ML communities, such as publications in top-tier venues, conference presentations, CVEs, or significant open-source projects.
This position is open to all candidates.