Senior AI Security Engineer AI/ML & LLM Security

Senior AI Security Engineer – AI/ML & LLM Security

Madison, NJ | Manhattan, NY | Boston, MA | Aventura, FL | Seattle, WA (Hybrid (3 onsite days/week)

6-Month Contract with the possibility of conversion to Full-Time Employment

Independent Consultants Only

About the Role:

This role combines strategic partnership, hands-on security engineering, AI infrastructure security, and automation. You will play a key role in defining and implementing the client's AI security strategy, ensuring that emerging AI capabilities, autonomous agents, and LLM-powered applications are developed and deployed securely at scale.

You will partner closely with AI platform, engineering, and security teams to establish security standards, build automated controls, assess emerging threats, and enable the responsible adoption of AI technologies across the company.

Key Responsibilities:

• Define the AI Security Roadmap: Own and develop the multi-year AI and agentic security roadmap, including vision, strategy, and standards, in collaboration with teams responsible for building the AI platform.
• Develop AI Security Controls: Design and implement technical security controls for AI systems, including autonomous agent blast-radius management, advanced prompt injection detection, and risk mitigation.
• Establish MCP Security Standards: Define centralized security standards for Model Context Protocol (MCP) and manage resilient MCP hosting infrastructure supporting autonomous AI agents.
• Conduct AI Red Teaming & Adversarial Assessments: Perform security assessments and adversarial testing of machine learning systems to identify vulnerabilities related to model manipulation, data extraction, and other AI-specific threats.
• Lead Threat Modeling & Architecture Reviews: Drive threat modeling initiatives and architectural evaluations for emerging AI capabilities, Retrieval-Augmented Generation (RAG) pipelines, and automated workflows.
• Evaluate Third-Party AI Security: Assess the security posture, privacy controls, and data retention policies of third-party foundation models, vector databases, and AI service providers.
• Drive AI Tooling & Risk Assessments: Serve as a primary technical advisor for evaluating AI tools and data classification requirements while developing standardized assessment frameworks to ensure compliance at scale.
• Establish AI Security Governance: Develop and scale AI security governance frameworks, organizational policies, and standardized practices to promote secure AI engineering across the company.
• Provide AI Security Guidance: Create and communicate practical AI security guidelines to help leadership, engineering teams, and cross-functional stakeholders adopt AI technologies safely.
• Implement Runtime AI Protection: Architect, deploy, and automate real-time protection mechanisms for LLM inputs and outputs, including prompt injection mitigation, jailbreak prevention, and response validation.

Required Qualifications & Skills:

• Professional Experience: 7+ years of experience in security engineering, with at least 2+ years focused on AI/ML and Large Language Model (LLM) application security.
• AI/ML Security Expertise: Deep understanding of transformer architectures, Retrieval-Augmented Generation (RAG), prompt engineering, and the OWASP Top 10 for LLM Applications.
• Cloud & Infrastructure Security: Strong technical proficiency in cloud security platforms such as AWS and Google Cloud Platform, containerization technologies such as Kubernetes, Identity and Access Management (IAM), and DevSecOps methodologies.
• Programming & Automation: Strong proficiency in Python or Go, with hands-on experience building production-grade integrations, security automation, and security pipelines.
• AI Threat Detection & Risk Management: Expertise in threat detection, security architecture, and adversarial machine learning risks, including prompt injection, model poisoning, and model manipulation.
• AI/ML Lifecycle Security: Hands-on experience securing the AI/ML development lifecycle, production deployments, and third-party AI supply chains.
• AI Security Governance: Working knowledge of AI governance frameworks, emerging regulatory requirements, and responsible AI practices.
• Strategic Communication: Strong communication skills with the ability to translate complex AI security risks into actionable technical roadmaps and measurable business impact for executive leadership.
• Security Engineering Mindset: Proactive and automation-first approach to identifying and addressing security gaps across complex AI/ML workflows.

Preferred Qualifications:

• Practical experience working with Model Context Protocol (MCP) frameworks and multi-agent autonomous systems.
• Understanding of AI-specific security and regulatory requirements, including:
• Data residency and location requirements.
• Data loss prevention and content protection policies for model outputs.
• Permission boundaries and access controls for autonomous AI agents.
• External OAuth authorization and permission scoping.
• Hands-on experience developing and implementing AI governance frameworks and AI enablement programs.
• Experience designing and securing enterprise AI platform architectures.
• Experience implementing automated AI security controls across complex, distributed environments.