Senior Security Engineer, AI/ML

Responsibilities

• Architect and manage LLM deployments across on-premises NVIDIA/AMD and cloud 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 while optimizing GPU utilization and resource isolation.
• Protect model weights, secure data ingestion, and harden inference endpoints across the MLOps lifecycle.
• Investigate and mitigate AI-specific threats including prompt injection, jailbreaking, and data poisoning.
• Map security testing findings to MITRE ATLAS, OWASP for LLMs, and STRIDE models.
• Bridge on-premises 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.
• At least 5 years of experience in AI/ML development, AI infrastructure engineering, or software development.
• At least 5 years of experience with Docker and Kubernetes.
• At least 5 years of experience with Python and libraries such as PyTorch, TensorFlow, or Hugging Face Transformers.
• Active Top Secret/SCI security clearance with current polygraph.
• Ability to travel up to 25% of the time.
• Preferred experience with AI/ML research or software development, LLM deployment frameworks such as vLLM, NVIDIA Triton, or Ollama, and agent development.
• Preferred knowledge of OWASP for LLMs or similar security frameworks, cloud-native AI services such as Google Vertex AI, and deployment of AI models on air-gapped or on-premises HPC systems.

Benefits

• Equity and benefits are provided.
• The role supports Google Public Sector customers and requires travel of up to 25%.