A/AI Machine Learning Engineering Stf - E4
Core
Design, plan, and perform Red Team assessments of AI systems to evaluate security, robustness, compliance, and trustworthiness across the AI lifecycle.
Role type
Senior AI/ML Red Team Engineer
Builds
Robust and secure AI/ML systems for mission-critical platforms
Domain
National Defense / AI Security
Deliverable
production ML models
Required skills
Python, Linux OS, AI/ML model development, adversarial testing, reverse engineering, NIST AI RMF, MITRE ATLAS
Preferred skills
Cybersecurity, vulnerability analysis, secure data engineering, LLM-based AI solutions, adversarial AI tools (PyRIT, Garak, BlackIce), MLOps/LLMOps
Technologies
TensorFlow, PyTorch, Scikit-Learn, PyRIT, Adversarial Robustness Toolkit, Garak, BlackIce
Responsibilities
Design and perform Red Team assessments of AI/ML model risks, data leakage, and governance; Develop tactics and procedures to evaluate system security and robustness; Collaborate with developers and cybersecurity teams to build secure systems; Define red teaming methodologies aligned with standards; Stay current on emerging threats and adversarial techniques.
Seniority
Senior, hands-on IC with technical leadership potential