Senior AI Engineer, Security Infrastructure

Air

United States

Hybrid

USD 180,000 - 240,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Air is seeking a Senior AI Engineer specializing in AI security to join our Agentic AI team as we scale capabilities across all levels of the U.S. government.

The role focuses on identifying vulnerabilities, designing defenses, and building durable security architecture for agentic systems. You will work with engineers building runtime, evaluation infra, and production AI systems, turning research into practical security improvements and automated evaluations.

Qualifications

  • 5+ years building production software, backend infra, distributed systems, security, or AI/ML infra.
  • Advanced degrees or equivalent practical experience in a related technical field.
  • Experience in AI red teaming, adversarial ML, offensive security, or security research.
  • Experience evaluating AI systems beyond basic prompt injection attacks.
  • Strong understanding of LLMs and agentic systems: inference, context, tooling, retrieval, multi-step execution.

Responsibilities

  • Research and develop AI red teaming, adversarial testing, security evaluation, and robust inference.
  • Threat model agentic architectures, identify trust boundaries and attack surfaces.
  • Design adversarial evaluations for prompts, tool abuse, privilege escalation, data exfiltration.
  • Build automated security evaluation and regression frameworks for agents, models, tools, and infra.
  • Translate attacks into production mitigations, secure architecture, and reusable controls.
  • Design secure execution environments for agents interacting with tools and data.
  • Hardening sandboxing and isolation for untrusted workloads.
  • Define capability boundaries and least-privilege access for agent tools and services.
  • Develop scalable AI infrastructure for secure model inference and agent execution.
  • Own and improve production infra across Kubernetes, AWS, networking, storage, compute.
  • Implement IAM, secrets, network isolation, containers, and service-to-service controls.
  • Build APIs and platform services to improve reliability and security.
  • Improve observability with logs, metrics, tracing, dashboards, telemetry, alerts.
  • Investigate complex failures across models, agents, distributed systems and infra.
  • Optimize performance and cost while maintaining reliability and security.

Skills

AI security
Distributed systems
Security assessments
AI/ML infrastructure
Agentic AI
Security research

Education

Bachelor's / Master's / Doctorate in CS or related field

Job description

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. By revealing true capacity, exposing real constraints, coordinating resources, and executing at the speed of operational demands, the front line gets what it needs to succeed.

Job Description

We are seeking an experienced Senior AI Engineer specializing in AI security to join our Agentic AI team as we scale our agentic capabilities across all levels of the U.S. government.

Over the past year, we have seen rapid adoption of our AI agent, Ace. As agents gain access to increasingly powerful tools, data, and workflows, securing these systems presents a fundamentally different set of challenges from securing traditional software.

AI security is not a solved problem. 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 will work directly with the engineers building our agent runtime, evaluation infrastructure, tools, and production AI systems. The goal is not simply to identify vulnerabilities - it is to turn what we learn into durable security architecture, automated evaluations, and engineering primitives that make our entire AI platform more secure.

This role is a full-time position located out of our office in Pittsburgh, PA or Arlington, VA and Remote for those outside of those cities.

This role may require up to 25% travel

Scope of Responsibilities
  • Research and develop new approaches to AI red teaming, adversarial testing, security evaluation, and robust inference.
  • Threat model agentic AI architectures, identifying trust boundaries, attack surfaces, privileged capabilities, and potential failure modes.
  • Design adversarial evaluations targeting threats such as prompt injection, indirect prompt injection, tool abuse, privilege escalation, data exfiltration, context or memory poisoning, and unintended agent behavior.
  • Build automated security evaluation and regression frameworks that continuously test agents, models, tools, and infrastructure against known and emerging attacks.
  • Translate successful attacks and research findings into production mitigations, architectural improvements, and reusable security controls.
  • Design secure execution environments for AI agents interacting with tools, code, data, and external systems.
  • Build and harden sandboxing and 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 identity and access management, secrets, network isolation, containers, and service-to-service communication.
  • Build scalable APIs, internal platform services, and infrastructure tooling that improve developer productivity, system reliability, and security.
  • Improve observability across AI systems through structured logging, metrics, distributed tracing, dashboards, security telemetry, and automated alerting.
  • Investigate complex production and security failures across models, agents, distributed systems, and infrastructure.
  • Optimize performance, latency, and infrastructure cost while maintaining strong reliability and security guarantees.
  • Stay current with emerging attacks against LLMs and agentic systems and rapidly translate relevant research into practical evaluations and defenses.
Qualifications

U.S. Citizenship is required

Required Skills:

  • 5+ years of experience building production software, backend infrastructure, distributed systems, security systems, or AI/ML infrastructure.
  • Bachelor's, Master's, or Doctorate in Computer Science, Computer Engineering, Cybersecurity, Data Science, or a related technical field, or equivalent practical experience.
  • Demonstrated experience in AI red teaming, adversarial machine learning, offensive security, systems security, or related security research.
  • Experience evaluating AI systems beyond basic direct prompt injection attacks.
  • Strong understanding of how modern LLM and agentic systems operate, including model inference, context management, tool use, retrieval, and multi-step agent execution.
  • Strong intuition for how AI syst
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior AI Engineer, Security Infrastructure
Senior AI Engineer, Security Infrastructure

Air • Arlington (VA), Pittsburgh

Hybrid
USD 170,000 - 250,000
Senior AI Engineer
Senior AI Engineer

Air • Arlington (VA), Pittsburgh

Hybrid
USD 150,000 - 210,000
Health benefits
Remote-friendly
Senior Forward Deployed Engineer, AI Security
Senior Forward Deployed Engineer, AI Security

AHEAD • United States

On-site
USD 150,000 - 210,000
Senior AI Engineer (FedD239)
Senior AI Engineer (FedD239)

defenseunicorns • Springfield (VA)

On-site
USD 140,000 - 210,000
Staff Security Software Engineer - Agentic Security Engineering
Staff Security Software Engineer - Agentic Security Engineering

Databricks Inc. • United States

Remote
USD 152,000 - 261,000
Comprehensive benefits package
Annual bonus potential
Equity
Principal Agent Security Engineer
Principal Agent Security Engineer

Fortinet, Inc. • Sunnyvale (CA)

On-site
USD 150,000 - 230,000
Senior Lead Security Engineer, AI
Senior Lead Security Engineer, AI

Testing Site - JPMC • Columbus (OH)

On-site
USD 140,000 - 210,000
Senior Security Engineer, Artificial Intelligence
Senior Security Engineer, Artificial Intelligence

InnoRev Technologies Inc • Irving (TX)

On-site
USD 150,000 - 210,000
Enterprise AI Engineer: Secure, Agentic Systems & LLMOps
Enterprise AI Engineer: Secure, Agentic Systems & LLMOps

Compunnel Inc. • Round Rock (TX)

Hybrid
USD 140,000 - 190,000
Sr. AI Security Engineer
Sr. AI Security Engineer

Backblaze • United States

Remote
USD 150,000 - 190,000
Remote LATAM role
Family healthcare
401(k)
+7