> Markdown version of [/jobs/ext/1449943-staff-ai-security-engineer](https://www.wearedevelopers.com/jobs/ext/1449943-staff-ai-security-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff AI Security Engineer

- **Company:** Okta, Inc.
- **Location:** New York, NY, United States
- **Experience:** Expert
- **Salary:** $180,000.0 - $247,500.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Amazon Web Services, Cloud Engineering, Cyber Security, Computer Programming, Programming Tools, Python (Programming Language), Open Web Application Security, Software Engineering, Data Streaming, Enterprise Software Applications, Build Management, Information Technology, Build Tools, Api Gateway, Automation Anywhere
- **Published:** July 26, 2026
- **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/17708039?backUrl=%2Fcareer%2F17708039%2FStaff-Ai-Security-Engineer-New-York-New-York

## About the Role

* AI Security Expertise: Deep knowledge of the AI threat landscape, including OWASP, MITRE ATLAS, NIST AI RMF with practical experience prompt injection, excessive agency, and other AI-related threats.
 * Software Engineering: 8+ years of experience in security engineering or backend software development, with strong coding proficiency in Python or Go and hands-on cloud experience.
 * Agentic Framework Knowledge: Experience securing or auditing agentic frameworks (such as LangChain, Strands, Claude Agent SDK, or custom tool-calling agents) operating within sandboxed environments.
 * Architectural Expertise: Proven ability to design scalable cloud infrastructure (AWS/GCP), API gateways, proxy architectures, and access controls for enterprise systems.
 * Paved Road Construction: Track record of building developer-first security tools and platform controls that maintain engineering velocity.
 * Technical Leadership: Strong communication skills with a history of driving technical strategy, influencing engineering leaders, and mentoring engineers.
 * Education: Bachelor's degree in Computer Science, Cybersecurity, Information Security, or equivalent practical experience

## Description

* Secure AI Implementations: Design and deploy enterprise AI guardrails, gateways, and other controls to protect our agentic workflows from emerging threats
 * Agent Hardening & Sandboxing: Establish security architectures for local and hosted agents to mitigate tool-calling, prompt injection, goal misalignment, and data exfiltration risks.
 * Define Paved Roads & Security Standards: Develop secure design patterns and developer tools that allow engineering teams to build and deploy AI features safely and quickly.
 * Threat Modeling for AI Workflows: Lead threat modeling and security reviews for agentic AI systems, enterprise deployments, and agent ecosystems.
 * AI Discovery & Visibility: Build systems to discover, inventory, and assess AI usage and data flows across the enterprise.
 * Agentic Platform Infrastructure: Design and operate internal AI security platforms and develop integrated AI capabilities that automate complex security operations.
 * Technical Leadership & Mentorship: Drive technical alignment across product, security, and infrastructure teams. Mentor engineers and security practitioners across domains


## Related Videos

- [Modern Data Architectures need Software Engineering](https://www.wearedevelopers.com/videos/1030-modern-data-architectures-need-software-engineering)
- [20 billion requests a week: Upgrading Twilio's API gateway at scale](https://www.wearedevelopers.com/videos/100234-20-billion-requests-a-week-upgrading-twilio-s-api-gateway-at-scale)
- [Thinking Differently - How to Make Money from Cyber Attacks & Cheats](https://www.wearedevelopers.com/videos/745-thinking-differently-how-to-make-money-from-cyber-attacks-cheats)
- [The New AI Security Stack: Observe, Detect, Protect](https://www.wearedevelopers.com/videos/100302-the-new-ai-security-stack-observe-detect-protect)
- [Building a framework-independent component library](https://www.wearedevelopers.com/videos/1679-building-a-framework-independent-component-library)
- [Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue](https://www.wearedevelopers.com/videos/1637-delay-the-ai-overlords-how-oauth-and-openfga-can-keep-your-ai-agents-from-going-rogue)

## Related Articles

- [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)
- [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)
- [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)