Senior AI Engineer, Security Infrastructure
Air · Arlington, Virginia, United States; Pittsburgh, Pennsylvania, United States; Remote
About this role
**Company Description** Air is the leader in Enterprise Readiness. Our mission is to establish readiness as a real-time condition that is continuously achieved. Today, a dangerous Readiness Gap exists between what the front line needs and what is delivered. Our AI-native platform, *Air Enterprise Readiness*, aligns development, production, delivery, and sustainment into one coordinated execution system for government agencies and industrial suppliers—revealing true capacity, exposing real constraints, coordinating resources, and executing at the speed of operational demands. **Job Description** We are seeking an experienced **Senior AI Engineer (AI Security)** to join our **Agentic AI** team as we scale our agentic capabilities across all levels of the U.S. government. As agents gain access to increasingly powerful tools, data, and workflows, securing these systems presents fundamentally different challenges than securing traditional software. This role sits at the intersection of **applied AI research, offensive security, and production systems engineering**. You will identify how agentic systems can fail or be exploited, develop new approaches for detecting and mitigating those failures, and build the infrastructure necessary to deploy capable AI agents securely in adversarial environments. You’ll work closely with engineers building our agent runtime, evaluation infrastructure, tools, and production AI systems—turning what you learn into durable security architecture, automated evaluations, and reusable engineering primitives. **Location / Travel** - Full-time role - Based out of **Pittsburgh, PA** or **Arlington, VA**, with **Remote** available for those outside those cities - Travel: **up to 25%** **Scope of Responsibilities** - Research and develop new approaches to **AI red teaming**, adversarial testing, security evaluation, and robust inference - Threat model agentic AI architectures: trust boundaries, attack surfaces, privileged capabilities, and failure modes - Design adversarial evaluations for threats such as **prompt injection**, **indirect prompt injection**, **tool abuse**, **privilege escalation**, **data exfiltration**, **context/memory poisoning**, and unintended agent behavior - Build automated security evaluation and regression frameworks to continuously test agents, models, tools, and infrastructure against known and emerging attacks - Translate successful attacks and research into production mitigations, architectural improvements, and reusable security controls - Design secure execution environments for agents interacting with tools, code, data, and external systems - Build and harden sandboxing/isolation mechanisms for executing agent-generated or otherwise untrusted workloads - Design capability boundaries, permission models, and least-privilege access controls for agent tools and services - Develop scalable AI infrastructure and services supporting secure model inference and agent execution - Own and improve production infrastructure across **Kubernetes, AWS, networking, storage, and compute** - Implement security controls around **IAM, secrets, network isolation, containers, and service-to-service communication** - Build scalable APIs, internal platform services, and infrastructure tooling to improve developer productivity, reliability, and security - Improve observability across AI systems via structured logging, metrics, distributed tracing, dashboards, security telemetry, and automated alerting - Inve
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.