Base: $60,000 - $80,000; bonus/equity: not specifi...
Hybrid
Ph.d. in computer science or related field
Experience with adversarial machine learning
Strong programming skills in python
This position focuses on advancing the science and practice of securing advanced AI systems against sophisticated adversaries such as large language models and reasoning systems
Job Summary
This position focuses on advancing the science and practice of securing advanced AI systems against sophisticated adversaries such as large language models and reasoning systems.
The successful candidate will contribute to frontier research spanning adversarial machine learning, secure AI deployment, and mechanistic interpretability within a mission-driven R&D environment.
Employees at ARLIS work on projects of critical importance to national security and are supported by a culture that values integrity, collaboration, and professional growth.
Matching Summary
This position focuses on advancing the science and practice of securing advanced AI systems against sophisticated adversaries such as large language models and reasoning systems.
Salary
Base: $60,000 - $80,000; Bonus/Equity: Not specified; Benefits: Regular Faculty benefits available
Skills & Requirements
Must-have
Ph.D. in Computer Science or related field
Experience with adversarial machine learning
Strong programming skills in Python
Experience with PyTorch or TensorFlow frameworks
Ability to obtain U.S. security clearance
Nice-to-have
Familiarity with white-box threat models
Experience with MLOps and distributed training
Knowledge of agentic system architectures
Background in national security applications
Record of publications in top-tier venues
Key Requirements
Ph.D. in Computer Science, Machine Learning, or Cybersecurity