About the company
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an Applied AI Security Engineer based in the United States.
Responsibilities
- Audit how AI tools and MCP integrations are being used across the organization, identifying connections to sensitive systems, data, credentials, and services to inform security policies.
- Design and implement layered AI security guardrails, including system-level prompts, scoped permissions, sandboxing approaches, and other controls that constrain AI behavior.
- Build and maintain an inventory of MCP servers, AI-to-service connections, and associated data-access permissions, with clear visibility into what each integration can access and why.
- Work directly with engineers and business users to embed secure-by-default practices into AI-assisted workflows and ensure security guidance translates effectively into day-to-day usage.
- Assess new AI tools, plugins, integrations, and access requests, identifying practical and secure ways to enable adoption.
- Continuously test, challenge, and red-team AI security controls to uncover vulnerabilities, bypasses, and gaps before they are exploited.
- Create clear documentation, security patterns, and guidance that can be understood and applied by audiences without a dedicated security background.
Requirements
- Bachelor's degree in Computer Science, Software Engineering, Cybersecurity, or a related technical field.
- Professional software development experience with strong fundamentals in services, APIs, authentication, authorization, permissions, and system integrations.
- Hands-on experience using AI coding or productivity tools such as Claude, GitHub Copilot, Gemini, or comparable solutions in business-critical workflows.
- Working knowledge of core security principles, including least privilege, sandboxing, trust boundaries, and foundational threat modeling.
- Strong communication and collaboration skills, with the ability to work alongside engineers and technical teams as a trusted security partner.
- Curiosity about emerging AI technologies and a practical understanding of their capabilities, limitations, and security implications.
- Experience with MCP (Model Context Protocol) or similar tool-calling and agent-integration frameworks is a strong plus.
- Familiarity with AI/LLM attack techniques such as prompt injection, jailbreaking, or related adversarial methods is advantageous.
- Experience in autonomous vehicles, robotics, or other safety-critical technology environments is a bonus.
Conditions
- US salary range: $139,000–$258,000 USD per year.
- Canada salary range: $118,000–$168,000 CAD per year.
- Competitive compensation package with discretionary equity incentive awards and annual performance bonuses.
- Medical, dental, and vision coverage, along with broader health and wellness benefits.
- Unlimited vacation.
- Flexible working hours and work-from-home support.
- Daily drinks, snacks, and catered meals when working from the office.
- Regular team-building activities and social events.
- An evolving benefits and perks program within a rapidly growing technology environment.
- Opportunities to work on advanced AI and autonomous technology challenges with a collaborative, innovative team.