Senior AI Security Engineer — Onsite in Miami

Compunnel, Inc.; Miami (FL); Hybrid; USD 150,000 - 210,000; Full time

Job summary

Compunnel, Inc. in Miami, FL is seeking a Senior AI Security Engineer to secure agentic AI capabilities across a modern eCommerce platform, protecting guest‑facing experiences and internal AI services.

The role spans runtime guardrails, identity-aware access, policy enforcement, and security controls from edge to AI runtime, requiring collaboration with product, platform, and AI/ML teams. This onsite contract position demands strong security leadership.

Qualifications

• 8+ years of experience in security engineering, application security, or platform security.
• Hands-on experience securing large-scale, consumer-facing eCommerce platforms.
• Strong understanding of web application and API security.
• Strong understanding of security architecture and application security principles.
• Deep knowledge of OAuth 2.0/2.1, OIDC, token-based authorization, and service principals.
• Experience designing fine-grained, least-privilege access models for distributed systems.
• Experience with Non-Human Identity (NHI) lifecycle management in highly dynamic environments.
• Experience working with AI-enabled or automation-heavy systems.
• Experience building AI solutions from start to finish.
• Familiarity with security risks unique to agentic and autonomous systems.
• Ability to reason about non-deterministic AI execution and enforce deterministic security controls.
• Knowledge of MCP security standards and agent runtime authorization.
• Experience with WAFs, API gateways, and edge security controls.
• Familiarity with cloud-native architectures and service-to-service security.
• Strong DevSecOps and Application Security experience.
• Ability to ensure consistent security enforcement across edge, API, service, and AI runtime layers.
• Ability to collaborate effectively with product, platform, AI/ML, and identity teams.
• Strong written and verbal communication skills with the ability to translate complex security concepts into practical guidance.

Responsibilities

• Design and implement security control planes for agentic AI systems.
• Define runtime authorization boundaries for AI agents, including tool-level access controls and least-privilege execution.
• Establish policy enforcement points governing agent behavior before high-impact actions.
• Support human-in-the-loop workflows for sensitive or high-risk AI-initiated actions.
• Design and review identity models for guests, employees, and non-human agent/workload identities.
• Implement or advise on OAuth/OIDC-based delegation and short-lived credential strategies.
• Ensure end-to-end attribution across user, agent, and tool execution chains.
• Secure guest-facing eCommerce flows including search, personalization, cart, and booking.
• Review backend service architectures supporting AI-driven eCommerce experiences.
• Promote agent-safe API patterns including idempotency, preview/apply, rollback, and rate limiting.
• Collaborate on edge security controls including WAFs, bot mitigation, and API gateways.
• Ensure consistent security enforcement from edge to API to service to AI runtime layers.
• Support secure cloud-native, containerized, and sandboxed deployment patterns across Google Cloud, AWS, and Azure.
• Define security telemetry and audit requirements for agentic AI systems.
• Support detection and response for runaway agents and excessive autonomy.
• Align AI security implementations with enterprise security standards and governance requirements.
• Build and secure AI solutions from end to end, from initial design through production implementation.

Skills

Security engineering

Web security

OAuth 2.0/OIDC

Least-privilege access

AI security

DevSecOps

Cloud security

Tools

WAFs

API gateways

Edge security

Job description

Compunnel, Inc. in Miami, FL is seeking a Senior AI Security Engineer to secure agentic AI capabilities across a modern eCommerce platform, protecting guest‑facing experiences and internal AI services.

The role spans runtime guardrails, identity-aware access, policy enforcement, and security controls from edge to AI runtime, requiring collaboration with product, platform, and AI/ML teams. This onsite contract position demands strong security leadership.