CO-OP Student (Cyber-Physical Systems) (January-June 2025)

Critical infrastructure, Internet of Things devices, Department of Defense (DoD) systems, communication systems, and traditional IT infrastructure all have one thing in common: their logical processing affects, and is affected by, the physical world. The Cyber-Physical Systems Group conducts research to understand the cybersecurity implications of these cyber-physical phenomena and develops first-of-their-kind prototypes for the Department of Defense, intelligence community, and federal agencies 

The Cyber Physical Systems Group tackles key problems in the convergence of cybersecurity and the physical world in an interdisciplinary research and development environment. We focus on cyber-physical sensing, cyber-physical effects, and red-teaming using techniques like building or applying advanced and novel sensors, digital processing, side-channel analysis, AI/ML, reverse engineering, system exploitation, and RF communications.

Position Overview:

We are seeking a highly motivated and independent CO-OP to support a research project focused on addressing distribution shift in machine learning models applied to RF (radio frequency) environments. This project explores the challenges of detecting and classifying small unmanned aerial systems (sUAS) in unknown and dynamic environments. The student will contribute to designing and executing experiments aimed at improving model performance when transitioning from lab environments to real-world deployment.

Key Responsibilities:

• Conduct independent research on machine learning models for RF environments and their performance in varying conditions.
• Design and implement experiments to test hypotheses related to signal propagation and model robustness.
• Analyze data to identify model failures, distribution shifts, and potential improvements.
• Collaborate with project leads to develop and validate solutions for sUAS detection and classification in the field.
• Document research methodologies, results, and findings effectively.

Required Skills:

• Strong foundation in applied mathematics and statistics.
• Experience with machine learning, including model training and evaluation.
• Proficiency in Python programming and relevant libraries (e.g., NumPy, TensorFlow, PyTorch, scikit-learn).
• Ability to work independently, break down complex problems, and devise creative solutions.
• Strong written and verbal communication skills for presenting research findings.

Preferred Qualifications:

• Familiarity with RF environments, signal propagation, or digital signal processing.
• Experience with software-defined radios (SDRs).
• Knowledge of sUAS detection and classification methods.
• Understanding of data preprocessing techniques and model evaluation metrics in dynamic environments.

Educational Requirements:

• Current enrollment in a relevant degree program (e.g., Computer Science, Applied Mathematics, Electrical Engineering, Data Science).

This is an excellent opportunity for a student to gain hands-on experience applying machine learning techniques to real-world RF challenges. If you're passionate about solving complex problems and have a keen interest in the intersection of RF and machine learning, we encourage you to apply.

To Apply:

Please submit your resume and a brief cover letter outlining your relevant experience and interest in the position. 

Selected candidate will be subject to a pre-employment background investigation and must be able to obtain and maintain a Secret level DoD security clearance.

MIT Lincoln Laboratory is an Equal Employment Opportunity (EEO) employer. All qualified applicants will receive consideration for employment and will not be discriminated against on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, veteran status, disability status, or genetic information; U.S. citizenship is required.

Requisition ID: 41662