Senior Lead Security Architect, AI​/ML Platforms

As a Senior Lead Cybersecurity Architect at JPMorgan

Chase within the Cybersecurity and Technology Controls organization, you are an integral part of a team that develops high-quality cybersecurity solutions for AI applications, AI agents, and platform products. You will drive measurable business impact by applying deep technical expertise and structured problem-solving methodologies to a diverse array of cybersecurity challenges spanning AI, Machine Learning, and agentic systems. You will partner with product, engineering, and risk stakeholders to identify emerging threats and implement scalable controls that enable responsible innovation.

You will help set technical direction through clear guidance, hands-on design reviews, and measurable risk reduction.

We are looking for an experienced AI Systems Cybersecurity Architect to join our team—not only as an AI/ML security subject matter expert, but as someone who is passionate about advancing safe and secure AI at enterprise scale. You'll work in a collaborative, trusting, thought-provoking environment that values diversity of thought and creative solutions aligned to our customers’ best interests. Best yet, you will join a team of highly motivated AI and security professionals who will help you build a strong foundation for a long-term career at JPMorgan

Chase.

• Develop and enhance security strategies, red teaming programs, and solution designs, while troubleshooting technical issues and creating scalable solutions across AI platforms, AI applications, and agentic workflows.
• Design secure, high-quality AI and software architectures, reviewing and challenging designs and code to ensure adversarial resilience, secure-by-default patterns, and appropriate compensating controls.
• Reduce AI, LLM, and agent security vulnerabilities by applying industry standards and emerging AI safety research, and by evolving policies, testing protocols, and technical controls across the full model development lifecycle (MDLC) and agent runtime.
• Collaborate with stakeholders across product, data science, cyber, legal, and risk to understand AI and agent use cases,drive alignment on AI risk tolerance and mitigation priorities, and recommend modifications during periods of heightened vulnerability, incident response, or regulatory change.
• Conduct discovery, threat modeling, and adversarial testing on generative AI, RAG pipelines, ML systems, and AI agents to identify vulnerabilities such as prompt injection, jail breaking, data poisoning, tool abuse, insecure memory/context handling, and unauthorized action execution.
• Define and assess agent security/safety controls, including authentication and authorization (authN/authZ) for users, services, and tools; secure session management; least-privilege tool access; and governance for tool/skill registration, enablement, and lifecycle management.
• Provide guidance on secure design, logging, monitoring, and observability for AI applications and agents, including auditability of prompts, tool calls, policy decisions, and model outputs, with controls to support detection, triage, and forensics.
• Evaluate and influence agent harness/orchestration patterns to ensure safe execution boundaries, reliable policy enforcement, and strong controls around delegation, automation, and human-in-the-loop requirements.
• Assess and secure integration patterns for Model Context Protocol (MCP) and similar tool-connection mechanisms, including authorization models, trust boundaries, data minimization, and controls to prevent exfiltration or unsafe tool invocation.
• Work with platform and cloud security teams to ensure secure infrastructure configuration and alignment with enterprise security architecture, including controls for AI/ML services and agent runtime dependencies.
• Engage with external researchers, vendors, and standards bodies to track emerging AI and agent threats, and translate best practices into actionable guidance and engineering guardrails.

• 5 years of applied experience in cybersecurity architecture and/or securing AI/ML systems, including architecture reviews and risk-based…