Senior Security Engineer, AI/ML, National Security, Public Sector

Google is seeking a Senior Security Engineer to help create and maintain secure operating environments for its public sector customers. The role focuses on securing AI/ML infrastructure across on-premises GPU clusters and cloud-native environments, including configuring deployments, protecting models and data, and developing defenses against adversarial manipulation.

Responsibilities:

• Architect and manage LLM deployments across on-premises (NVIDIA/AMD) and cloud (cloud computing platform, Google Cloud platform (GCP) environments. Audit multi-agent orchestration, agent construction, and vector databases to map data flows and enforce privilege boundaries
• Use Docker and Kubernetes to orchestrate scalable inference and training environments, optimizing Graphics Processing Unit (GPU) utilization and resource isolation
• Protect model weights, secure data ingestion, and harden inference endpoints across the Machine Learning operations (MLOps) lifecycle
• Investigate and mitigate AI-specific threats (e.g., prompt injection, jailbreaking, data poisoning). Map testing findings to MITRE ATLAS, OWASP for LLMs, and STRIDE models
• Bridge local high-compute clusters and cloud AI services while maintaining a consistent security posture

Requirements:

• Bachelor's degree in Computer Science, Data Science, Artificial Intelligence, or a related technical field or equivalent practical experience
• 5 years of experience in AI/ML development, AI infrastructure engineering, or software development
• 5 years of experience with containerization (Docker) and orchestration (Kubernetes)
• 5 years of experience with Python and with libraries like PyTorch, TensorFlow, or Hugging Face Transformers
• Ability to travel up to 25% of the time as needed
• Must possess an active Top Secret/SCI security clearance with current polygraph
• Applicants must work 5 days per week on-site in Fort Meade, Maryland
• 5 years of experience in AI/ML research or software development
• Experience with LLM deployment frameworks such as vLLM, NVIDIA Triton, or Ollama and agent development
• Knowledge of open worldwide application security project (OWASP) for LLMs or similar security frameworks
• Familiarity with cloud-native AI services (e.g., cloud computing platform, Google Vertex AI)
• Track record of deploying AI models on air-gapped or on-premises high-performance computing (HPC) systems