Postdoctoral Associate – AI Security

UM01 University of Maryland College Park (UMCP); United States; On-site; USD 70,000 - 90,000; Full time

Job summary

The UM01 University of Maryland College Park is seeking a Postdoctoral Associate in AI Security to conduct innovative research intersecting machine learning, cybersecurity, and national security.

This role involves original research in AI security, developing robust AI systems, and requires a Ph.D. in a relevant field. Candidates must demonstrate research experience and strong programming skills. Opportunity to work with experts in national security applications.

Qualifications

• Ph.D. in a relevant technical field is required.
• Demonstrated research experience in machine learning or AI security.
• Strong programming skills in Python and experience with ML frameworks.

Responsibilities

• Conduct original research in AI security.
• Develop and evaluate novel attack and defense techniques.
• Collaborate with interdisciplinary teams.

Skills

Research experience in machine learning

Strong programming skills in Python

Experience with ML frameworks

Ability to work collaboratively

Education

Ph.D. in Computer Science or related field

Tools

PyTorch

TensorFlow

Job description

Job Description Summary

The Applied Research Laboratory for Intelligence & Security (ARLIS) at the University of Maryland is seeking a Postdoctoral Associate in AI Security to conduct cutting‑edge research at the intersection of machine learning, cybersecurity, and national security.

Key Responsibilities

• Conduct original research in AI security, including adversarial machine learning, model robustness, and secure AI system design.
• Develop and evaluate novel attack and defense techniques for modern AI systems, covering mechanistic and white‑box analysis, multi‑turn adaptive adversarial interactions, and security of reasoning models and agent‑based architectures.
• Design and implement experimental frameworks for evaluating AI system vulnerabilities across deployment scenarios such as open‑weight, API‑based, and hybrid systems.
• Apply interpretability techniques (circuit analysis, feature attribution, sparse autoencoders) to understand internal model behavior and failure modes.
• Contribute to the development of benchmarks, evaluation methodologies, and datasets for AI security research.
• Collaborate with interdisciplinary teams including machine learning researchers, systems engineers, and national security domain experts.
• Translate research findings into actionable insights for government sponsors, including technical reports and briefings.
• Publish research in leading conferences and journals such as NeurIPS, ICML, ICLR, IEEE S&P, CCS.
• Obtain a U.S. security clearance and meet all requirements for access to classified information.

Research Areas of Interest

• Adversarial AI & Red Teaming – adaptive, multi‑turn attacks and reasoning‑based adversarial strategies; evaluation of model robustness under realistic threat models.
• Secure AI Systems & Deployment – security of agentic systems, tool use, and multi‑model architectures; supply chain and fine‑tuning risks in open‑weight models.
• AI Evaluation & Benchmarking – development of security‑focused benchmarks and evaluation pipelines; measurement of robustness, safety degradation, and attack transferability.
• Mechanistic AI Security – circuit‑level analysis of safety and capability mechanisms; feature geometry, representation learning, and interpretability‑driven security.

Work Environment & Impact

• Engage in high‑impact research directly supporting national security missions.
• Work alongside leading experts in AI, cybersecurity, and intelligence applications.
• Access to advanced computing infrastructure and unique government‑relevant problem sets.
• Opportunity to shape emerging standards and practices for securing advanced AI systems.
• Balance of publishable academic research and mission‑driven applied work.

Minimum Qualifications

• Ph.D. in Computer Science, Machine Learning, Cybersecurity, or a related technical field.
• Demonstrated research experience in machine learning (deep learning, LLMs, reinforcement learning), adversarial machine learning or AI safety/security, systems security, applied cryptography, or cyber operations.
• Strong programming skills in Python and experience with ML frameworks such as PyTorch or TensorFlow.
• Experience designing and executing empirical research, including experimentation and evaluation.
• Ability to work in a collaborative, interdisciplinary research environment.
• Ability to obtain and maintain a U.S. security clearance.

Preferences

• Familiarity with white‑box threat models and evaluation of open‑weight AI systems.
• Experience with MLOps or large‑scale training infrastructure, including distributed training, GPU clusters, or ML experimentation platforms.
• Knowledge of AI system deployment architectures such as RAG systems, multi‑agent systems, or tool‑augmented models.
• Experience with adversarial evaluation frameworks, red‑teaming methodologies, or benchmark development.
• Experience with mechanistic interpretability and/or alternative approaches to understanding model internals (e.g., activation analysis, circuit‑level reasoning, representation learning).
• Background in national security applications, including work with DoD, IC, or federally funded research programs.
• Record of publications in top‑tier conferences or journals.

Physical Demands

Sedentary work performed in a normal office environment; may occasionally lift or carry objects up to 10 pounds. Ability to attend meetings both on and off campus and spend long hours in front of a computer screen.

EEO Statement

The University of Maryland, College Park is an Equal Opportunity Employer. All qualified applicants will receive equal consideration for employment. Please read the University’s Equal Employment Opportunity Statement of Policy.