Design and execute white-box attacks against advanced AI models, checkpoints, post-training systems, reward functions, data pipelines and evaluation environments.
Locations (2)
Redmond, Washington, United States
United States
Compensation
Research Sciences IC5 - The typical base pay range for this role across the U.S. is USD $142,800 - $274,800 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $188,000 - $304,200 per year.
Responsibilities
Design and execute white-box attacks against advanced AI models, checkpoints, post-training systems, reward functions, data pipelines and evaluation environments.
Investigate adversarial behavior including jailbreaks, harmful permissiveness, reward hacking, deceptive behavior, capability elicitation, privacy leakage, data poisoning and model supply-chain compromise.
Build high-fidelity experiments and automated attack suites that reproduce realistic threats and run continuously against new checkpoints and system configurations.
Develop rigorous threat models, attack hypotheses and reproducible evidence; assess severity, exploitability and customer or governance impact.
Partner with model scientists, engineers and product security teams to identify root causes and drive findings to verified remediation.
Requirements
Doctorate in relevant field
Master's Degree in relevant field
Bachelor's Degree in relevant field
Nice to have: hands-on expertise in adversarial machine learning
Responsible for conducting quantitative analytics and modeling projects for specific business units or risk types within Global Risk Analytics, developing models, processes, and documentation to support risk and capital management.
Locations (3)
Charlotte, United States
Chicago, Illinois, United States
Jersey City, New Jersey, United States
Compensation
$89,800.00 - $151,200.00 annualized salary, offers to be determined based on experience, education and skill set. Discretionary incentive eligible. This role is eligible to participate in the annual discretionary plan.
Responsibilities
Performs end-to-end market risk stress testing including scenario design, implementation, results consolidation, internal and external reporting, and analyzes stress scenario results
Supports planning related to setting quantitative work priorities in line with the bank’s overall strategy and prioritization
Identifies continuous improvements through reviews of approval decisions on relevant model development or model validation tasks
Supports model development and model risk management in respective focus areas to support business requirements and the enterprise's risk appetite
Supports methodological, analytical, and technical guidance to influence strategic direction and tactical approaches of development/validation projects
Requirements
Master’s degree in Math, Economics, Statistics, or similar discipline
PhD in Math, Economics, Statistics, or similar discipline
