Senior AI Security Researcher

What you'll do

• Own hands-on post-training research projects for open-weight language models used for cybersecurity tasks.
• Develop and curate training data, objectives, and experimental controls for model training.
• Assess supervised, preference-based, and reinforcement-learning methods for model optimization.
• Implement reproducible training pipelines and track datasets, configurations, checkpoints, and evaluation results.
• Develop and evaluate recursive self-improvement methods for training language models.
• Deliver trained model artifacts and reusable workflows for red-team partners to evaluate and apply.

What we're looking for

• Bachelor's degree with 4+ years experience, Master's with 3+ years, or Doctorate with 1+ year in a related field.
• Equivalent experience to the required degree and years of experience.
• Ability to pass Microsoft Cloud Background Check and other government security screenings.
• Prior experience training open-weight language models with distributed or multi-GPU infrastructure (preferred).
• Prior experience with preference optimization or reinforcement-learning-based post-training (preferred).
• Prior experience evaluating language models in adversarial or security-focused settings (preferred).
• Peer-reviewed publications or released research software in language-model training, post-training, or AI security (preferred).
• 2+ years of experience with Python and machine learning frameworks (preferred).