Staff Security Engineer – AI - R01573022

Brillio•Seattle, WA

10h

About The Position

Brillio is seeking an experienced AI Security Engineer to drive AI and LLM security initiatives, establish security standards, and implement technical controls across AI/ML platforms, agentic AI systems, and enterprise AI applications. The role combines strategic security leadership, hands-on engineering, AI infrastructure protection, and automation. The engineer will work with AI platform, engineering, and security teams to define security roadmaps, mitigate emerging AI threats, and establish secure-by-design practices throughout the AI development lifecycle.

Requirements

At least 7 years of experience in information security, cybersecurity, or security engineering, including at least 2 years focused on AI/ML security or LLM application security.
Strong understanding of transformer architectures, LLMs, RAG, prompt engineering, agentic AI and autonomous AI workflows, and the OWASP Top 10 for LLM Applications.
Deep technical expertise in cloud security, particularly AWS and GCP, including IAM, containerization, Kubernetes, and DevSecOps methodologies.
Hands-on experience with AI/ML security architectures, production AI deployments, and securing the end-to-end AI development lifecycle.
Strong knowledge of AI-specific security threats, including prompt injection, jailbreak attacks, model poisoning, model manipulation, sensitive data exposure, and data extraction.
Experience implementing threat detection, security architecture controls, and automated security mechanisms for AI/ML environments.
Proficiency in Python or Go, including experience developing production-grade integrations, security automation tools, and security pipelines.
Experience assessing third-party AI platforms, foundation models, and AI technology supply chains.
Working knowledge of AI governance frameworks, emerging regulatory requirements, data privacy, and Responsible AI principles.
Strong analytical and problem-solving skills, including the ability to identify and address security gaps across complex AI/ML workflows.
Excellent communication and stakeholder-management skills, including the ability to translate AI security risks into technical roadmaps and business impact for executive leadership.

Nice To Haves

Hands-on experience with Model Context Protocol (MCP) frameworks and autonomous multi-agent AI systems.
Understanding of AI-related data residency and data localization requirements.
Understanding of data loss prevention and content protection controls for AI-generated outputs.
Understanding of permission boundaries and access restrictions for autonomous AI agents.
Understanding of external OAuth authorization and access-scoping mechanisms.
Experience developing and implementing enterprise AI governance frameworks and AI enablement programs.
Background in designing and implementing AI platform security architectures.
Experience establishing security standards and governance models for enterprise-wide AI adoption.

Responsibilities

Define and drive the long-term AI and Agentic AI security roadmap, including security architecture, technical standards, and implementation strategies in collaboration with AI platform and engineering teams.
Design and implement security controls for AI environments, including autonomous agent permissions, blast-radius management, and prompt-injection detection.
Establish centralized security standards for Model Context Protocol (MCP) implementations and oversee secure, resilient MCP hosting infrastructure for autonomous AI agents.
Conduct adversarial security assessments and AI red-team exercises across machine-learning systems to identify vulnerabilities involving model manipulation, data extraction, and unauthorized access.
Lead threat modeling and security architecture assessments for emerging AI capabilities, RAG pipelines, autonomous workflows, and AI-powered applications.
Evaluate the security posture, privacy controls, data-handling practices, and retention policies of third-party foundation models, AI platforms, and vector databases.
Advise on AI tooling evaluations and data-classification initiatives, and develop standardized security assessment frameworks for risk management and compliance.
Establish and scale AI security governance frameworks, technical policies, and organizational standards for secure and responsible AI engineering.
Develop and communicate practical AI security guidelines to engineering teams, business stakeholders, and leadership.
Architect, deploy, and automate real-time security controls for LLM inputs and outputs, including prompt-injection prevention, jailbreak detection, and AI response validation.