Senior AI Security Engineer

Vertex Inc.•Remote - PA, PA

1d•$120,700 - $156,900

About The Position

The AI Security Engineer is a hands-on technical role responsible for securing the AI systems, models, and pipelines that power Vertex's products. The role partners with product engineering, platform, governance, and information security teams to identify, assess, and mitigate risks related to large language models, retrieval-augmented generation, agentic workflows, and the AI supply chain. It operates at the intersection of offensive research, defensive engineering, and policy, translating the evolving AI threat landscape into concrete, measurable controls. The role designs and deploys security capabilities for AI and Agentic AI systems, performs security reviews and vulnerability analysis, and conducts AI-focused red team testing. It also develops security automation and secure-by-default patterns, guides developers on agentic security and privacy practices, monitors emerging threats, and supports AI security incident response and cross-team program delivery.

Requirements

At least 5 years of experience in security engineering, application security, AI/ML engineering, or security architecture, with hands-on experience securing AI/ML or LLM-based systems.
Ability to independently lead security reviews for complex AI systems and drive mitigation plans across engineering teams with limited oversight.
Practical experience assessing AI-specific risks, including prompt injection, insecure output handling, sensitive data exposure, excessive agency, model and data supply chain weaknesses, and unsafe retrieval or memory patterns.
Advanced understanding of AI system behavior, including model vulnerabilities, evaluation results, and security-relevant failure modes.
Proficiency in Python or an equivalent language for security automation, evaluation scripts, test harnesses, and evidence-collection workflows.
Working knowledge of modern AI stacks, including model APIs, orchestration frameworks, vector databases, retrieval pipelines, and agentic workflows, and at least one major cloud platform (AWS, GCP, or Azure).
Familiarity with AI security and governance frameworks such as OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, and ISO/IEC 42001.
Strong written and verbal communication skills for technical and non-technical audiences.

Nice To Haves

Experience leading AI red team engagements, test-and-evaluation activities, secure AI design reviews, or product security programs across multiple teams.
Experience deploying, integrating, or securing AI/ML systems in production or customer-facing environments outside a lab setting.
Hands-on experience with AI security tooling, model scanning, or custom evaluation harnesses.
Background in cloud security, IAM, application security, data protection, logging/monitoring, incident response, or security operations for production systems.
Experience coordinating technical work across product, platform, and security stakeholders.
External contributions, presentations, or publications in AI security, adversarial AI, AI assurance, or secure AI engineering.
Equivalent combinations of education, training, and relevant professional experience are accepted in lieu of a formal degree.

Responsibilities

Design, develop, and deploy security capabilities that protect AI and Agentic AI systems.
Perform threat modeling, security reviews, and vulnerability analysis across LLM-enabled applications, RAG systems, inference pipelines, and agentic workflows.
Conduct hands-on and automated red team testing focused on AI-specific risks, document reproducible failure modes, and drive durable mitigations with engineering teams.
Build and extend AI security automation, evaluation harnesses, and secure-by-default patterns for AI system design, development, deployment, and least-privilege agent configurations.
Define agent coordination, delegation, and escalation patterns, and guide developers on security and privacy best practices for agentic coding and MCP-enabled tooling.
Monitor emerging AI threats and platform changes, translate relevant risks into prioritized controls, and ensure full system traceability using identity, security, and logging frameworks.
Serve as the AI security incident subject matter expert, providing rapid triage, root-cause analysis, and proactive collaboration with defensive security teams.
Identify and resolve cross-team technical risks and dependencies to sustain AI security program delivery.