Principal AI Security Engineer

Zip Co Limited

3h • $203,000 - $254,000 • Remote

About The Position

Join Zip’s Security team to lead the technical direction for securing AI applications, autonomous agents, and AI-enabled engineering workflows. This hands-on engineering role focuses on designing and implementing scalable security controls that enable teams to build and operate AI-powered systems without unnecessary risk. The role combines architectural leadership with practical engineering, including writing code and turning complex AI security challenges into production-ready solutions.

The engineer will define security architecture and standards for LLM applications, RAG systems, agents, and AI-powered products; build protections and secure-by-default patterns; and develop testing, evaluation, monitoring, and automation capabilities. The role partners closely with engineering, platform, and security teams, including the Agentic Platform team, to carry solutions from architecture through production and support safe innovation at scale. It also includes mentoring engineers and influencing technical decisions across teams.

This is a remote-first opportunity for US-based employees, with the option to work in person from Zip’s Manhattan office. The annual base pay range is $203,000–$254,000 under Zip’s US national compensation band; additional premium percentages may apply. Total compensation may include bonus and/or commission awards and benefits. Visa sponsorship is not available.

Requirements

• Demonstrated Staff- or Principal-level technical leadership in security engineering, application security, or cloud security.
• Deep security engineering experience and demonstrable hands-on work with LLM or agent systems, such as production systems, open-source work, internal platforms, or published research.
• Intimate familiarity with the OWASP Top 10 for LLM Applications, MITRE ATLAS, and NIST AI RMF.
• Strong understanding of LLM architectures, agentic systems, RAG, and modern AI development frameworks.
• Experience building AI security evaluations, red-teaming capabilities, or model security gateways, and securing AI systems against prompt injection, data leakage, tool abuse, and unauthorized access.
• Strong software engineering skills, including proficiency in Python or another modern programming language.
• Experience with cloud-native architectures, APIs, containers, IAM, and modern software delivery practices.
• Ability to design and implement security controls, automation, and reusable engineering components.
• Experience threat modeling complex systems and translating security requirements into practical solutions.
• Strong technical leadership skills and ability to influence architecture and engineering decisions across teams.
• A builder’s mindset focused on automation, scalability, and secure-by-default engineering.

Nice To Haves

• Experience with LangChain, LangGraph, Semantic Kernel, OpenAI APIs, Azure AI, Google Vertex AI, or similar technologies.
• Experience securing MCP servers, autonomous coding agents, or agentic workflows.
• Familiarity with the OWASP Top 10 for LLM Applications, MITRE ATLAS, and NIST AI RMF.
• Experience with Microsoft Azure, Google Cloud Platform (GCP), Terraform, Kubernetes, and CI/CD security.
• Experience in financial services, payments, or other regulated environments.

Responsibilities

• Define and implement security architecture for LLM applications, RAG systems, autonomous agents, and AI-powered products.
• Engineer protections against prompt injection, data exfiltration, insecure tool execution, excessive agency, and other AI-specific threats.
• Establish secure patterns for model access, non-human identity (NHI) access, authorization, secrets management, and sensitive data protection.
• Design security boundaries for AI agents interacting with enterprise systems, APIs, databases, and cloud infrastructure.
• Establish secure-by-default patterns that let developers adopt AI without bypassing security controls.
• Develop secure harnesses and guardrails for AI coding assistants, autonomous development agents, and AI-generated software.
• Secure MCP servers, agent tool integrations, and AI-enabled development workflows.
• Build reusable security components, APIs, and automation that integrate with engineering platforms and CI/CD pipelines.
• Build automated security testing and evaluation capabilities for AI applications and agents.
• Develop AI red-teaming, prompt-injection testing, and security regression-testing approaches.
• Implement monitoring and detection for suspicious AI behavior, unauthorized tool execution, and sensitive data exposure.
• Respond to incidents involving agent misalignment, such as exceeding authority or taking unauthorized actions, and partner with the Agentic Platform team on controls to prevent recurrence.
• Use AI to automate security engineering activities, including threat modeling, vulnerability analysis, and remediation.
• Establish Zip’s technical direction and engineering standards for AI security.
• Partner with engineering teams to take secure AI solutions from architecture through production.
• Design risk-tiering logic aligned with Zip’s five-level AI automation classification.
• Co-own the security evaluation framework for new AI models and third-party tools; evaluate emerging technologies and make pragmatic build-versus-buy decisions.
• Mentor engineers and influence technical decisions across security, platform engineering, and software development.

Benefits

• Flexible working culture
• Incentive programs
• Unlimited PTO
• Generous paid parental leave
• Leading family support policies
• Company-sponsored 401(k) match
• Learning and wellness subscription stipend
• Beautiful Union Square office with a casual dress code
• Employer-sponsored insurance for employees and dependents, with several 100% Zip-covered choices available

What This Job Offers

• Job Type: Full-time
• Career Level: Principal
• Education Level: No Education Listed