Senior AI Engineer, Security Infrastructure

Jobtailor; Pennsylvania; On-site; USD 180,000 - 260,000; Full time

Job summary

Jobtailor is seeking a senior security engineer to design and implement robust AI safety and security workflows across production systems. You will lead adversarial testing, threat modeling, and infrastructure hardening for multi-cloud environments, collaborating with AI researchers and platform engineers to translate research into production defenses.

You will own scalable security evaluation frameworks, improve observability, and drive secure execution environments, IAM, and zero-trust

Qualifications

• U.S. Citizenship required.
• 5+ years building production software, backend infra, distributed systems, security systems, or AI/ML infrastructure.
• Advanced degree or equivalent practical experience accepted.
• Demonstrated AI red teaming, offensive security, or security research experience.
• Experience evaluating AI systems beyond basic prompt injection attacks.
• Strong understanding of LLMs, agentic systems, and multi-step execution.
• Proficient Python and production-grade software development.

Responsibilities

• Research and develop approaches to AI red teaming, adversarial testing, security evaluation, and robust inference.
• Threat model agentic AI architectures, trust boundaries, and failure modes.
• Design adversarial evaluations for prompt injection, tool abuse, and data exfiltration.
• Build automated security evaluation and regression frameworks for agents, models, tools, and infra.
• Translate attacks into production mitigations and reusable security controls.
• Design secure execution environments, sandboxing, and least-privilege controls.
• Own and improve production infrastructure across Kubernetes, AWS, networking, storage, and compute.
• Implement IAM, secrets management, and network isolation controls.
• Build scalable APIs and platform services with robust observability.
• Investigate production and security failures across models, agents, and distributed systems.

Skills

AI Red Teaming

Adversarial ML

Threat Modeling

Python Programming

Distributed Systems

Security Evaluation

Education

Bachelor's / Master's / PhD in CS / CE / Cybersecurity or related field

Tools

Kubernetes

AWS

GCP

Azure

CI/CD

MicroVMs

Container Isolation

IAM

Secrets Management

Job description

• Research and develop 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 prompt injection, tool abuse, privilege escalation, data exfiltration, poisoning, and unintended agent behavior
• Build automated security evaluation and regression frameworks for agents, models, tools, and infrastructure
• Translate attacks and research findings into production mitigations, architectural improvements, and reusable security controls
• Design secure execution environments, sandboxing, isolation mechanisms, capability boundaries, permission models, and least-privilege controls
• Develop scalable AI infrastructure and services for secure model inference and agent execution
• Own and improve production infrastructure across Kubernetes, AWS, networking, storage, and compute
• Implement controls for IAM, secrets, network isolation, containers, and service-to-service communication
• Build scalable APIs, internal platform services, and infrastructure tooling
• Improve observability through structured logging, metrics, distributed tracing, dashboards, security telemetry, and automated alerting
• Investigate production and security failures across models, agents, distributed systems, and infrastructure
• Optimize performance, latency, and infrastructure cost while maintaining reliability and security
• Track emerging attacks against LLMs and agentic systems and translate research into evaluations and defenses
• Collaborate directly with engineers building the agent runtime, evaluation infrastructure, tools, and production AI systems

Requirements

• U.S. Citizenship is required
• 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 modern LLM and agentic systems, including model inference, context management, tool use, retrieval, and multi-step agent execution
• Experience threat modeling complex systems and translating risks into engineering controls
• Strong programming experience in Python and production-quality software development
• Experience operating production services on Kubernetes and cloud platforms such as AWS, GCP, or Azure
• Strong understanding of networking, distributed systems, containers, service orchestration, and scalable architectures
• Experience designing APIs, services, asynchronous systems, and event-driven architectures
• Ability to debug failures spanning application code, AI models, distributed systems, and infrastructure
• Ability to move between research and engineering, validating attacks or defenses experimentally and turning results into production systems
• Experience with AI agent runtimes and tool-execution environments
• Experience with secure code execution sandboxes, container isolation, microVMs, or other untrusted-workload mechanisms
• Experience with cloud security, infrastructure hardening, IAM, secrets management, network isolation, and zero-trust architectures
• Experience with offensive security, penetration testing, vulnerability research, or exploit development
• Experience developing automated adversarial evaluations or integrating security evaluations into CI/CD pipelines
• Experience with adversarial machine learning, model robustness, or inference-time defenses
• Familiarity with MITRE ATLAS, OWASP LLM/GenAI guidance, or the NIST AI Risk Management Framework
• Experience securing RAG systems, vector stores, model gateways, or other modern AI infrastructure components
• Experience with software supply-chain security and securing model, dependency, and container artifacts
• Experience working in government, defense, or other high-security environments

Core Competencies

Demonstrates expertise in AI red teaming, adversarial machine learning, and security evaluation, with a strong focus on building and securing production infrastructure across cloud platforms and distributed systems. Proficient in threat modeling, designing secure execution environments, and implementing robust security controls for AI systems.

Highest-signal resume keywords

• AI Red Teaming
• Adversarial Machine Learning
• Kubernetes
• Cloud Security
• Python Programming

Hard Skills

• Threat Modeling
• Adversarial Testing
• Security Evaluation
• Automated Security Frameworks
• API Design
• Distributed Systems
• Infrastructure Hardening
• Vulnerability Research
• Model Inference
• Event-Driven Architectures

Soft Skills

• Collaboration
• Problem-Solving
• Research and Engineering Transition

Industry Keywords

• Cybersecurity
• AI Infrastructure
• High-Security Environments
• MITRE ATLAS
• NIST AI Risk Management Framework

Tools & Technologies

• AWS
• GCP
• Azure
• CI/CD Pipelines
• MicroVMs
• Container Isolation
• IAM
• Secrets Management
• Zero-Trust Architectures
• Observability Tools