Job Description:
AI Security Engineer
AI Risk Research & Landscape Monitoring
Track new developments, capabilities, and attack techniques in the AI space, and translate them into concrete risks for Fireblocks.
Build and maintain a living threat model for AI usage across the company, covering the platform, internal tooling, and third-party AI services.
AI Usage Discovery & Risk Assessment
Analyze how AI is used across Fireblocks — in the platform, by developers (e.g., coding assistants), by corporate and business users, and through AI tools brought in via procurement.
Assess the configuration and security posture of AI systems and tools in use, and identify and prioritize gaps.
AI Security Architecture & Tooling
Design and propose new tooling, configurations, and projects that reduce AI-related risk.
Architect and implement the resulting solutions end-to-end, partnering with engineering teams where needed.
Build and operate the AI security infrastructure that makes AI usage across Fireblocks secure by default.
Open-Weight Models for Security Operations
Research open-weight model implementations for use in security workflows.
Deploy open-weight models to support the incident response teams in investigating and responding to security incidents in real time.
Job Requirements:
3+ years of experience spanning AI/ML, with hands-on exposure to both.
3+ years of experience in engineering / RnD roles.
Strong knowledge of cloud infrastructure (AWS in particular) and how AI workloads run in production.
Strong understanding of AI/ML system architecture — model deployment, inference infrastructure, RAG, pipelines, and agent frameworks.
Hands-on experience configuring and rolling out leading AI tools and platforms for a broad internal audience.
Experience working with open-weight/open-source models in production or research settings.
A genuine builder mentality — a track record of designing, shipping, and operating security tooling or infrastructure end-to-end, not just advising on it.
Excellent communication skills and the ability to work independently while coordinating closely with Security, R&D, and other stakeholders.
Nice to Have
Familiarity with AI security frameworks such as the OWASP Top 10 for LLM Applications, NIST AI RMF, or MITRE ATLAS.
Experience with SOC/IR tooling, threat intelligence, or offensive security.
Benefits:
/
