Director, Cyber Security Architect

BNYLake Mary, FL
Onsite

About The Position

At BNY, our culture allows us to run our company better and enables employees’ growth and success. As a leading global financial services company at the heart of the global financial system, we influence nearly 20% of the world’s investible assets. Every day, our teams harness cutting-edge AI and breakthrough technologies to collaborate with clients, driving transformative solutions that redefine industries and uplift communities worldwide. Recognized as a top destination for innovators, BNY is where bold ideas meet advanced technology and exceptional talent. Together, we power the future of finance – and this is what #LifeAtBNY is all about. Join us and be part of something extraordinary. We’re seeking a future team member for the role of AI Security Architect to join our Cybersecurity team. This role will be based in New York City.

Requirements

  • 12 years in cybersecurity/enterprise security architecture with 3 years focused on AI/ML or data platform security at scale.
  • Expertise in cloud security (AWS/Azure/GCP) including identity, secrets management, key management (KMS/HSM), network segmentation, and policy-as-code.
  • Strong knowledge of AI/ML workflows: data ingestion/feature engineering, model training/inference, MLOps tooling (model registry, orchestrators, serving).
  • Practical experience with adversarial ML concepts and defenses; familiarity with model robustness, prompt injection risks, and secure evaluation methods.

Responsibilities

  • Define enterprise AI security architecture: develop reference architectures, guardrails, and standards for secure data pipelines, model training/inference, and AI-integrated applications across on-prem and cloud.
  • Secure MLOps/ML platforms: architect identity, secrets management, network segmentation, and least-privilege access for feature stores, model registries, orchestration, and deployment pipelines.
  • Data protection by design: establish controls for sensitive data ingestion, anonymization/pseudonymization, encryption (at rest/in transit), tokenization, and lineage across AI workflows.
  • Adversarial ML defense: design controls and tests for model poisoning, evasion, model theft/exfiltration, prompt injection, jailbreaking, data leakage, and output manipulation.

Benefits

  • highly competitive compensation
  • benefits
  • wellbeing programs
  • access to flexible global resources and tools
  • generous paid leaves
  • paid volunteer time
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service