Senior AI Security Engineer - Remote, Production Systems

Openkrill; United States; Hybrid; USD 180,000 - 280,000; Full time

Job summary

Air in the United States seeks a Senior AI Engineer focused on AI security to advance agentic capabilities and secure deployments for government-scale workloads. You will research red teaming, design secure runtimes, and build automated evaluation frameworks across models, tools, and infrastructure.

You will collaborate with engineers building agent runtimes, evaluation systems, and production AI services, delivering durable security architecture and practical defenses while maintaining strong

Qualifications

• 5+ years building production software, backend infra, or AI/ML infra.
• Strong grounding in AI red teaming and offensive security.
• Experience securing AI systems beyond basic prompt injections.
• Proficiency with Python and production-grade software.
• Experience operating on Kubernetes and cloud platforms (AWS/GCP/Azure).
• Ability to model threats and translate risks into controls.

Responsibilities

• Research adversarial testing and robust evaluation for AI systems.
• Threat model agentic architectures and identify attack surfaces.
• Design and run automated security evaluations for agents and tools.
• Develop secure execution environments and sandboxing.
• Improve production infrastructure across Kubernetes, AWS, networking, storage, and compute.
• Create scalable APIs and internal platform services with security in mind.
• Enhance observability, telemetry, and automated security alerts.

Skills

Python

AI security

Red teaming

Offensive security

Kubernetes

Cloud platforms

LLM security

Threat modeling

Distributed systems

CI/CD

Education

Bachelor's degree or higher in CS/CE/Cybersecurity

Tools

Docker

AWS

GCP

Azure

Job description

Air in the United States seeks a Senior AI Engineer focused on AI security to advance agentic capabilities and secure deployments for government-scale workloads. You will research red teaming, design secure runtimes, and build automated evaluation frameworks across models, tools, and infrastructure.

You will collaborate with engineers building agent runtimes, evaluation systems, and production AI services, delivering durable security architecture and practical defenses while maintaining strong