AI Security Architect (New York)

Job Title: AI Security Architect

Job Type: Fulltime

Client Location: New York, NY

Work Arrangement: Onsite Position from day one

Must Have Technical/Functional Skills

• AI and GenAI security architecture
• Secure LLM deployment patterns
• AI/ML threat modeling and security risk assessment
• Prompt injection, jailbreak, data leakage, and model abuse controls
• Retrieval-Augmented Generation security
• Vector database and embedding security
• AI agents, tool access, plugins, and API security
• Sensitive-data protection, DLP, encryption, and access control for GenAI
• AI model and software supply-chain security
• AI red teaming, security testing, monitoring, and incident response
• AI governance and Responsible AI controls
• NIST AI Risk Management Framework and OWASP guidance for LLM applications
• Azure OpenAI, AWS Bedrock, Google Vertex AI, or comparable platforms
• Financial services, model-risk, or regulated-industry experience

Roles & Responsibilities

• Define secure reference architectures and deployment patterns for AI and GenAI solutions.
• Perform threat modeling and risk assessments for LLM, RAG, agentic AI, and machine-learning use cases.
• Design safeguards against prompt injection, jailbreaks, sensitive-data exposure, insecure output handling, and unauthorized tool use.
• Establish security controls for model access, training and grounding data, vector stores, APIs, plugins, and AI agents.
• Define AI security governance, control standards, design-review criteria, and risk-acceptance processes.
• Partner with data, cloud, privacy, model-risk, application-security, and business teams.
• Lead AI security assessments, proofs of concept, red-team exercises, and executive workshops.
• Monitor emerging AI threats and translate them into practical enterprise security controls.
• Support proactive opportunity mining and development of AI security offerings.

Generic Managerial Skills, If any

• Executive and client stakeholder communication
• AI security advisory and workshop facilitation
• Cross-functional leadership
• Emerging-risk analysis
• Security roadmap and control-framework development
• Presales, solution development, and opportunity identification
• Ability to translate technical AI risks into business language