Staff Security Engineer – AI - R01573022

About Brillio:

Brillio is one of the fastest growing digital technology service providers and a partner of choice for many Fortune 1000 companies seeking to turn disruption into a competitive advantage through innovative digital adoption. Brillio, renowned for its world-class professionals, referred to as "Brillians", distinguishes itself through their capacity to seamlessly integrate cutting-edge digital and design thinking skills with an unwavering dedication to client satisfaction.

Brillio takes pride in its status as an employer of choice, consistently attracting the most exceptional and talented individuals due to its unwavering emphasis on contemporary, groundbreaking technologies, and exclusive digital projects. Brillio's relentless commitment to providing an exceptional experience to its Brillians and nurturing their full potential consistently garners them the Great Place to Work® certification year after year.

Staff Security Engineer – AI

Primary Skills

• SAP GRC, Nessus, Information Security & Cybersecurity, Cloud Security, Archer, Metasploit, Wireshark, Burpsuite, AWS Secrets Manager, Nmap, PaaS - Security, CxSAST, Web Application Scanning (WAS), ServiceNow GRC, AppScan

Job requirements

• We are looking for an experienced AI Security Engineer who can drive AI and LLM security initiatives, establish security standards, and implement robust technical controls across AI/ML platforms, agentic AI systems, and enterprise AI applications. This role combines strategic security leadership, hands-on engineering, AI infrastructure protection, and automation. The individual will work closely with AI platform, engineering, and security teams to define security roadmaps, mitigate emerging AI threats, and establish secure-by-design practices across the AI development lifecycle. Key Responsibilities This role will focus on AI security strategy, engineering, governance, and automation.

  • AI Security Strategy and Roadmap: 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.

  • AI Infrastructure Security: Design and implement technical security controls to protect AI environments, including autonomous agent permissions, blast radius management, and advanced prompt injection detection.

  • Model Context Protocol (MCP) Security: Establish centralized security standards for Model Context Protocol (MCP) implementations and oversee secure, resilient MCP hosting infrastructure supporting autonomous AI agents.

  • AI Red Teaming and Adversarial Testing: Conduct adversarial security assessments and AI red teaming exercises across machine learning systems to identify vulnerabilities related to model manipulation, data extraction, and unauthorized access.

  • Threat Modeling and Architecture Reviews: Lead threat modeling initiatives and security architecture assessments for emerging AI capabilities, Retrieval-Augmented Generation (RAG) pipelines, autonomous workflows, and AI-powered applications.

  • Third-Party AI Security Assessments: Evaluate the security posture, privacy controls, data handling practices, and retention policies of third-party foundation models, AI platforms, and vector databases.

  • AI Risk Assessment and Compliance: Serve as a technical advisor for AI tooling evaluations and data classification initiatives. Develop standardized security assessment frameworks to ensure consistent risk management and compliance.

  • AI Security Governance: Establish and scale AI security governance frameworks, technical policies, and organizational standards to promote secure and responsible AI engineering practices.

  • Security Enablement: Develop and communicate practical AI security guidelines, helping engineering teams, business stakeholders, and leadership safely adopt and leverage AI technologies.

  • LLM Security and Runtime Protection: Architect, deploy, and automate real-time security controls for LLM inputs and outputs, including prompt injection prevention, jailbreak detection, and AI response validation.

Know what it’s like to work and grow at Brillio: Click here