Senior AI Model Security Researcher

Microsoft • Redmond, WA

2d • $119,800 - $261,000

About The Position

Microsoft Security is seeking Senior AI Model Security Researchers to join a new red team spanning adversarial machine learning, model integrity, offensive security, automation, and privacy. The role involves hands-on red teaming of advanced AI models and the training and evaluation systems around them, designing attacks that expose exploitable model behavior, and turning critical findings into durable improvements such as regression evaluations, adversarial environments, stronger controls, and safety training data.

The role calls for researchers who can move between scientific investigation and operational security work. Success requires depth in adversarial machine learning or offensive security, fluency across the broader AI system, and the judgment to produce reproducible evidence that research, engineering, product, and independent review teams can act on.

Requirements

• Doctorate in a relevant field, or a master's degree in a relevant field and 3+ years of related research experience, or a bachelor's degree in a relevant field and 4+ years of related research experience, or equivalent experience.
• Must be able to meet Microsoft, customer, and/or government security screening requirements, including passing the Microsoft Cloud Background Check upon hire or transfer and every two years thereafter.

Nice To Haves

• Hands-on expertise in adversarial machine learning, AI security, model evaluation, privacy attacks, offensive security, or a closely related discipline.
• Experience designing experiments or security investigations that produce reproducible technical evidence and actionable remediation.
• Programming and research-prototyping ability sufficient to build attack tooling, evaluation harnesses, and automated tests.
• Experience testing large language models, post-training or reinforcement-learning systems, agentic systems, or AI-enabled security products.
• Knowledge of reward modeling, interpretability, capability elicitation, data extraction, poisoning, privacy, or model supply-chain security.
• Experience with cyber exploitation, cloud or identity security, sandboxing, secure evaluation environments, or offensive-security operations.
• Demonstrated ability to communicate complex attack paths, severity, and residual risk to researchers, engineers, and senior decision-makers.
• Experience converting research findings into production evaluations, mitigations, training interventions, or security controls.

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.
• Convert confirmed weaknesses into regression evaluations, adversarial training or RL environments, safety training data, and stronger technical controls.
• Communicate findings and residual risk clearly to technical teams, leadership, and independent reviewers.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior