Agentic Security Engineer

The Agentic Security Engineer at NXP Semiconductors is responsible for securing agentic AI systems, autonomous workflows, AI orchestration frameworks, and AI-driven tool execution environments across enterprise and engineering domains. This role emphasizes the security of runtime execution, agent orchestration, Model Context Protocol (MCP) integrations, tool invocation mechanisms, and autonomous decision-making processes.

The Agentic Security Engineer will work closely with AI engineering, platform engineering, enterprise security, and architecture teams to help ensure agentic systems are deployed securely and in alignment with NXP security standards, runtime control requirements, and applicable regulatory expectations.

The ideal candidate brings hands-on experience in runtime security, AI orchestration technologies, API security, policy enforcement, and distributed systems security, along with a strong understanding of risks such as prompt injection, unsafe tool execution, unauthorized actions, context manipulation, memory poisoning, and insecure agent behavior.

This position will support the design and implementation of runtime security controls, AI agent monitoring, action validation mechanisms, execution tracing, and scalable guardrails for autonomous and semi-autonomous AI systems., * Translate security requirements and operational risks into runtime enforcement and execution control mechanisms

• Contribute to secure adoption of agentic AI capabilities aligned with enterprise security and governance requirements
• Support security architecture discussions for AI orchestration platforms and autonomous systems
• Perform security assessments of agentic AI systems, orchestration frameworks, and enterprise integrations
• Review integrations involving MCP servers, APIs, plugins, external tools, and enterprise platforms

2.AI Runtime Monitoring and Operational Security

• Build and enhance observability capabilities including execution tracing, logging, auditing, and monitoring for AI agent activity
• Support detection capabilities for insecure agent behavior, unsafe tool execution, and anomalous AI runtime activities
• Contribute to runtime visibility, investigation support, and operational security practices for AI orchestration environments
• Support monitoring controls for autonomous decision-making and AI-driven execution workflows

3.Collaboration, Risk Management, and Secure AI Operations

• Collaborate with Enterprise, Security, Platform, DevOps, and AI engineering teams to support secure deployment of agentic AI systems
• Assess risks related to unsafe tool execution, unauthorized actions, prompt injection, context manipulation, memory poisoning, and insecure agent behavior
• Support implementation of security controls aligned with NIST AI RMF, OWASP Top 10 for LLM Applications, and secure agentic AI practices
• Assist in evaluating agentic AI systems for compliance with internal security requirements and applicable regulations
• Provide security guidance related to autonomous workflows, tool integrations, runtime controls, and secure orchestration practices

Bachelor’s degree in computer science, Cybersecurity, Engineering, Information Technology, or a related field

Advanced degrees such as Masters are preferred, * 5+ years of experience in cybersecurity, application security, runtime security, or related engineering roles

• 2+ years of experience securing or supporting AI/ML/GenAI applications, platforms, or services
• Hands-on experience with AI/ML platforms, APIs, orchestration frameworks, or AI-assisted development environments and cloud platforms such as AWS and Azure
• Experience supporting runtime monitoring, observability, or security operations in distributed systems environments is considered a plus

Technical Skills

• Solid understanding of AI/ML/GenAI concepts, including AI agents, orchestration frameworks, MCP integrations, memory systems, and autonomous workflows
• Strong knowledge of runtime security concepts such as policy enforcement, action validation, execution tracing, and delegated authority controls
• Familiarity with AI-related risks, including unsafe tool execution, prompt injection, memory poisoning, context manipulation, and insecure agent behavior
• Working knowledge of the OWASP Top 10 for LLM Applications, MITRE ATLAS, and NIST AI RMF
• Understanding of API security, IAM, observability, logging, and runtime monitoring principles

Soft Skills

• Strong analytical and problem-solving skills
• Excellent communication and collaboration abilities
• Ability to manage multiple initiatives in a fast-paced environment

NXP is a global player in Semiconductor industry, and security is an essential and integral part of our business.