Security Engineer, AI

Applied Systems, Inc.•,

4d•$80,000 - $120,000•Remote

About The Position

Applied Systems is building out its AI security program and seeking an experienced security engineer to help secure its Large Language Models, generative AI systems, and ML infrastructure. This is an emerging role for an engineer who understands traditional security principles deeply and is eager to apply them to the rapidly evolving world of AI, from prompt injection and model poisoning to data privacy in training pipelines. You won't need to be an ML researcher or data scientist, but you should have foundational knowledge of how machine learning works and be genuinely curious about AI-specific security threats. This role offers the opportunity to shape how Applied approaches AI security, work with cutting-edge technology, and grow expertise in an area where few security engineers have deep experience. Ideal for someone who values both hands-on security work and the challenge of learning an emerging domain.

Requirements

Minimum of 3-5 years' experience in security engineering or DevSecOps roles
Demonstrated foundational understanding of machine learning concepts, ML workflows, and common frameworks (PyTorch, TensorFlow, scikit-learn)
Working knowledge of Large Language Models, transformer architectures, and generative AI applications
Experience with or strong understanding of LLM security concerns (prompt injection, jailbreaking, data poisoning, model extraction)
Experience with container security, Kubernetes security, and securing AI workloads in containers
Knowledge of cloud security in AI contexts (GPU security, distributed training security, data protection in ML pipelines)
Understanding of secure software development practices and supply chain security as applied to ML models
Knowledge of model governance, versioning, and secure model deployment
Experience with infrastructure-as-code technologies (Terraform, Ansible)
Experience with one or more scripting languages (Python, Bash, Go)
Understanding of encryption, key management, and data privacy (especially PII in training data)
Familiarity with vulnerability scanning and secure code practices
Working knowledge of compliance frameworks and their application to AI systems (GDPR, SOC 2, etc.)
Experience with securing data pipelines and ETL processes
Excellent written and verbal communication skills
Demonstrated ability to work independently and as part of a team
Willingness to rapidly learn new AI technologies and security frameworks

Nice To Haves

Certification in security (Security+, CISSP, etc.)
Experience with specific LLM platforms (OpenAI API, Anthropic Claude, Google Vertex AI, Azure OpenAI)
Experience with ML security tools and platforms (Robust Intelligence, Arthur AI, etc.)
Participation in AI security research, publications, or conferences
Experience in threat modeling for AI systems
Background in security research or penetration testing
Experience with red-teaming AI systems

Responsibilities

Evaluate and assess the security posture of Large Language Models (LLMs) and generative AI systems used within or by Applied Systems
Conduct threat modeling and security architecture reviews for AI/ML systems and their data pipelines
Implement and maintain security controls for AI model training, fine-tuning, and inference infrastructure
Develop and maintain security baselines and hardening configurations for AI platforms and frameworks
Identify and help remediate security vulnerabilities specific to AI/ML systems (prompt injection, model poisoning, data exfiltration, adversarial attacks)
Implement data security and privacy controls for AI training datasets and inference inputs
Develop and maintain security runbooks for AI systems incident response
Participate in security reviews of AI/ML applications and vendor AI services
Contribute to the development of internal AI security policies and guidelines
Assist with proof-of-concept builds for AI security solutions and controls
Stay current with emerging AI security threats, research, and industry best practices
Contribute to internal security training related to AI risks and secure AI development