Full Stack Lead Security Engineer

JPMorgan Chase is hiring for a Full Stack Lead Security Engineer position supporting Cybersecurity & Technology Controls for AI/ML. This onsite role in Plano, TX focuses on building secure software and strengthening AI and LLM security through practical red teaming, secure architecture, and automated adversarial testing. You will help deliver tamper-proof, audit-defensible solutions while working closely with teams across product, data science, cyber, legal, and risk.

What you’ll do

• Develop and improve security strategies, red teaming programs, and solution designs, including troubleshooting technical issues and producing scalable outcomes.
• Design secure, high-quality AI and software architectures, reviewing designs and code to ensure adversarial resilience.
• Lower AI and LLM security vulnerabilities by applying industry standards and emerging AI safety research, updating policies, testing protocols, and controls.
• Partner with stakeholders across product, data science, cyber, legal, and risk to understand AI use cases and recommend changes during periods of heightened vulnerability or regulatory shifts.
• Automate discovery and adversarial testing for generative AI, RAG pipelines, and ML systems to identify issues such as prompt injection , jailbreaking , and data poisoning .
• Provide guidance on secure design, logging, monitoring, and compensating controls for AI applications and platforms.
• Define and implement AI red teaming methodologies, playbooks, and success metrics, enabling continuous testing and safe rollout of new AI models and features.
• Collaborate with platform and cloud security teams to ensure secure infrastructure configuration and alignment with enterprise security architecture.
• Track emerging AI threats by engaging with external researchers, vendors, and standards bodies, and bring best practices into the organization.
• Contribute to a team culture that emphasizes diversity, opportunity, inclusion, and respect .
• Work within a cross-functional environment to build relationships, influence senior stakeholders, and drive alignment on AI risk tolerance and mitigation priorities.

Required qualifications

• Formal training or certification covering Public Cloud environment concepts and advanced hands-on experience with cloud-native AI services such as Bedrock .
• Practical experience with Infrastructure as Code (IaC) , including Terraform and CloudFormation .
• Proficiency in Python scripting.
• Strong understanding of AI/ML concepts and trends , including foundational knowledge of AI red teaming to design and implement exercises for complex AI architectures.
• Ability to conceptualize, design, validate, and communicate creative technical solutions for enterprise-level security problems, including building internal tools, dashboards, and automation for red teaming.

Technologies you may use

• Bedrock
• Terraform
• CloudFormation
• Python
• PyRIT
• Garak
• MITRE ATLAS
• OWASP Top 10 for LLMs
• IAM, Authentication
• OIDC, SAML

Benefits

• Competitive total rewards package including base salary determined based on role, experience, skill set, and location.
• Eligible roles may receive commission-based pay and/or discretionary incentive compensation, paid in cash and/or forfeitable equity.
• Comprehensive health care coverage.
• On-site health and wellness centers.
• Retirement savings plan.
• Backup childcare.
• Tuition reimbursement.
• Mental health support.
• Financial coaching.

Preferred qualifications, capabilities, and skills

• Expertise in planning, designing, and implementing AI red teaming exercises and enterprise-level security solutions for generative AI, LLMs, and ML systems.
• Experience using specialized AI security and red teaming tools and frameworks such as PyRIT , Garak , and custom LLM evaluation harnesses, including contributions to AI security or open-source security projects.
• Experience with threat modeling, discovery, vulnerability, and penetration testing such as MITRE ATLAS and OWASP Top 10 for LLMs , plus foundational cybersecurity concepts including IAM and Authentication with OIDC and SAML .