This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
train, test, deploy, and maintain models that learn from data
own and define the direction of mission-critical solutions by applying best-fit ML algorithms and technologies
collaborate with network analysts to deliver world class solutions to conduct red team evaluations of machine learning systems, including LLMs
use intelligence analysis to evaluate exploitation risks and operational impacts
Requirements
Experience with Python for building automated red-team tests or evaluations
Experience with Linux and containerized environments, such as Docker or Docker Compose, to operate model‑testing or red‑team tooling
Experience with red-team methodologies, including stress‑testing, structured prompts, failure‑mode discovery, vulnerability identification, or behavior scoring
Experience with AI or ML evaluation or security testing
Ability to analyze ML or LLM outputs, identify misbehavior or data leakage patterns, and document findings clearly
Ability to synthesize technical evidence with intelligence context and communicate risk to both technical and non‑technical audiences
TS/SCI clearance with a polygraph
Bachelor's degree and 3+ years of experience with AI or ML, or 6+ years of experience with AI or ML in lieu of a degree
Nice to have
Experience with red‑teaming LLM systems
Experience applying AI or ML red‑team results to operational intelligence workflows, including TTP mapping, adversary‑capability analysis, or mission COA development
Knowledge of enterprise AI Security offerings and tooling ecosystem used to probe ML and LLM systems
Knowledge of data‑fusion, anomaly‑detection, or analytic‑augmentation methods used in modern intelligence environments
What we offer
health, life, disability, financial, and retirement benefits