Machine Learning Security Research Fellow

Currently pursuing or recently completed (within 2 years) a PhD in machine learning, computer science, statistics, or related field Strong research credentials through publications, preprints, workshop papers, or significant open-source contributions Strong hands-on experience with modern AI/ML frameworks (PyTorch, JAX, TensorFlow), foundation models, and AI/ML research workflow Demonstrated ability to think adversarially about systems Proficient in Python and comfortable with systems programming Self-directed researcher capable of defining research questions and driving projects

Pursue own AI/ML security research interests Evaluate security of state-of-the-art AI/ML systems Design and implement new attack methodologies and defensive techniques Build and release AI/ML security tools and frameworks Collaborate with security research team and work on client engagements