Research Assistant

Title:

Research Assistant Employee Classification:

Non-Pos Hourly Posting Code Campus:

University of North Texas Division:

UNT-Provost SubDivision-Department:

UNT-College of Music Department:

UNT-College of Music-Gen-134000

Job Location:

Denton Salary:

$20.00 an hour

FTE:

0.48

Retirement Eligibility:

Not Retirement Eligible About Us

• Values Overview Welcome to the University of North Texas System.

The UNT System includes the University of North Texas in Denton and Frisco, the University of North Texas at Dallas and UNT Dallas College of Law, and University of North Texas Health Fort Worth. We are the only university system based exclusively in the robust Dallas-Fort Worth region. We are growing with the North Texas region, employing more than 14,000 employees, educating a record 49,000+ students across our system, and awarding nearly 12,000 degrees each year. We are one team comprised of individuals who are committed to excellence, curiosity and innovation. We are transforming lives and creating economic opportunity through education. We champion a people-first values-based culture where We Care about each other and those we serve. We believe that we are Better Together because we foster an environment of respect, belonging, and access for all. We demonstrate Courageous Integrity through setting exceptional standards and acting in the best interest of our communities. We are encouraged to Be Curious about opportunities for learning, creating, discovering, and innovating, and are encouraged to learn from failure. Show Your Fire by joining our team and exhibiting your passion and pride in your work as part of our UNT System team. Learn more about the UNT System and how we live our values at www.

UNTSystem.edu . Department Summary The Division of Vocal Studies in the College of Music is hiring a Research Intern to assist with Vocal Pedagogy research. Position Overview As a Research Intern, this employee will support the development and continuous improvement of a deep learning pipeline designed to analyze laryngostroboscopic imaging of singers. This includes organizing and preprocessing video and frame data, fine-tuning vision models, deploying an end-to-end inference workflow, integrating human-in-the-loop feedback, and drive model performance towards =90% accuracy. The research assistant will also help to co-mentor student researchers involved in the project. Minimum Qualifications Master's degree (or equivalent experience) in Computer Science, Data Engineering, Machine Learning, Biomedical Imaging, or related field. Knowledge, Skills and Abilities

• Proficiency in Python and deep-learning frameworks (PyTorch or TensorFlow/Keras), plus libraries such as timm, XGBoost, MoviePy, Pandas, NumPy.
• Hands-on experience with vision backbones (transformers and/or advanced CNNs) and multi-output regression.
• Strong skills in image/video preprocessing, class balancing, and model checkpoint management.
• Familiarity with human-in-the-loop feedback workflows and active-learning strategies. Preferred Qualifications
• Experience containerizing or deploying ML services using Docker, FastAPI, or Streamlit.
• Knowledge of experiment-tracking tools (TensorBoard, MLflow).
• Excellent written and verbal communication; proven ability to collaborate in interdisciplinary teams.
• Background in laryngeal imaging, stroboscopy, or voice science. Required License/Registration/Certifications Job Duties Data Management & Preprocessing
• Organize and version raw and processed videos/frames in local storage and OneDrive using structured manifests and Git / DVC.
• Implement balanced sampling and augmentation pipelines to correct class imbalance (Mode, Density, Color). Model Development & Training
• Fine-tune and experiment with state-of-the-art vision backbones (e.g., Vision Transformer, Swin/ConvNeXt, EfficientNet, 3-D CNNs, Hybrid CNN-Transformers) to classify Mode, Density, and Color.
• Extract deep visual features and evaluate a variety of downstream learners (e.g., XGBoost, fully connected nets, tabular transformers, ensemble regressors) to predict all 32 physiological rating parameters.
• Run 25+ epoch training cycles in VS Code or Google Colab with systematic checkpointing and metrics logging. Video Processing Pipeline
• Develop scripts that autonomously parse raw laryngostroboscopic video files and extract frames for the corresponding Class and Subclass.
• For each extracted frame, run the trained pipeline to classify Mode, Density, and Color, then predict all 32 positional rating parameters.
• Collate results-including generated timestamps, class labels, and ratings-into a single Excel report matching the original Training Data Sheet's structure Human-in-the-Loop Feedback Integration
• Build an interactive CLI / Streamlit interface so users can confirm or correct model predictions.
• Store verified feedback and schedule periodic retraining to incorporate corrections, driving accuracy toward = 90%.

. Physical Requirements Communicating with others to exchange information. Repeating motions that may include the wrists, hands and/or fingers. Sedentary work that primarily involves sitting/standing. Environmental Hazards No adverse environmental conditions expected. Work Schedule Workload will be hours 20 per week. Meet weekly with faculty supervisor to evaluate progress. Employment is for one year pending continued grant funding. Driving University Vehicle No Security Sensitive This is a Security Sensitive Position. Special Instructions Applicants must submit a minimum of two professional references as part of their application. If needed, additional references can be added after the application has been submitted. Benefits For information regarding our Benefits, click here . EEO Statement The University of North Texas System is firmly committed to equal opportunity and does not permit

• and takes actions to prevent
• discrimination, harassment (including sexual violence, domestic violence, dating violence and stalking), and retaliation on the basis of race, color, religion, national origin, sex, age, disability, genetic information, or veteran status in its application, employment practices, and facilities; nor permits race, color, national origin, religion, age, disability, veteran status, or sex discrimination and harassment in its admissions processes, and educational programs and activities.

UNT System Administration promptly investigates complaints of discrimination, harassment, and related retaliation and takes remedial action when appropriate. System Administration also takes actions to prevent retaliation against individuals who oppose any form of harassment or discriminatory practice, file a charge or report, or testify, assist, or participate in a related investigation or proceeding.