CV

Education

• Ph.D in Systems Engineering, University of Virginia, 2024
• M.Eng. in Electrical Engineering, Virginia Tech, 2016
• B.S. in Electrical and Electronics Engineering, North South University, 2012

Research Experience

• Research Assistant |Human AI-Technology Lab, University of Virginia | Aug 2020 – July 2025 • Designed a novel spatio-temporal representation for wearable sensor data, delivering 21% accuracy gain in one-shot inference while enhancing interpretability through signal visualizations • Created novel ranking framework for early-stage analysis of sparse sensor data, boosting depression prediction recall by 13% on limited multimodal datasets • Built ML pipeline achieving 9x error reduction (RMSE 2.83 vs 25.7) through personalized modeling of mobile/fitness sensor data for mental health prediction

• Research Assistant | VICTOR Lab, Virginia Tech, UVA | Aug 2018 – Aug 2020 • Developed patented autonomous sorting system with computer vision algorithm, reducing logistics center workload by 75% • Engineered path planning and computer vision solutions for unmanned ground vehicles for international robotics competition

• Research Fellow | Wireless@VT Lab, Virginia Tech| Aug 2016 – Aug 2018 • Investigated reinforcement learning (multi-armed bandit) algorithms optimizing wireless spectrum access for DARPA Spectrum challenge 2. • Implemented comprehensive testing frameworks for spectrum sharing models, supporting DARPA competition requirements

Industry Experience

• Data Science & Analytics Intern | Sage Therapeutics | May 2023 – Aug 2023 • Built an unsupervised predictive model (Variational Autoencoder, TensorFlow) to analyze unstructured clinical data (sleep cycles, EEG, ECG) for patient segmentation based on drug efficacy • Identified 3 clinically meaningful patient groups through clustering analysis, supporting targeted insights of drug on sleep • Reduced clinical data processing times by 73% (30 min → 8 min) by streamlining data workflows. Partnered with cross-functional teams to define KPIs and optimize patient clustering for outcome prediction

• Data Science Intern | Argonne National Laboratory | May 2022 – Aug 2022 • Engineered high-throughput Python pipelines to process 50+ GB/day of vehicular data by leveraging Dask for scalability to model mobility patterns • Designed modular, object-oriented ingestion frameworks to support model governance principles for team compliance • Built standardized data dictionaries and integrated scalable SQL pipelines to streamline analytics across distributed systems • Developed model evaluation modules to validate machine learning model performance across production datasets

Teaching Expereience

• Instructor – AP Computer Science & Robotics – The Montgomery Academy

  • Teaching AP Computer Science Principles (Python) & AP Computer Science A (Java) to 40+ students. • Leading AI-integration initiatives to prepare students and teachers for responsible use of AI in pedagogy. • Mentoring students toward college-level research projects and competitions. Tenure: Aug 2025 - Present

• Graduate Teaching Assistant - University of Virginia

  • Deep Learning (DS 6050) | Enrollment: 50 • Taught graduate students fundamentals and applications of deep learning across various disciplines. • Covered topics: regularization, optimization, convolutional networks, sequence modeling, generative learning, instance-based learning, and deep reinforcement learning. Tenure: Jan 2024 – May 2024, Aug 2023 – Dec 2023, Jan 2022 – May 2022

  • Data and Information Engineering (SYS 2202) | Enrollment: 180 • Instructed and guided two sections of 80 undergraduate students in RDBMS, data modeling, and web-based data dissemination. • Topics included SQL, Entity Diagrams, XML, semantic modeling, web-enabled database systems. Tenure: Jan 2023 – May 2023

  • Applied Mathematics – Single Variable Calculus II (APMA 110) | Enrollment: 90 • Lectured on advanced integration techniques with applications in physics including work, fluid force, and center of mass. • Covered: improper integrals, Simpson’s Rule, Taylor series, numerical methods, parametric equations, and polar coordinates. Tenure: Aug 2020 – Dec 2020

  • Statistical Learning and Graphical Methods (ECE 6501 / CS 4501) | Enrollment: 60 • Led graduate and undergraduate students through advanced probabilistic models and computational techniques. • Topics included graphical models, Bayesian methods, expectation-maximization, and variational inference. Tenure: Jan 2020 – May 2020

  • Robotic Autonomy (MAE 4260) | Enrollment: 40 • Taught principles of autonomous robotic systems and navigation in unstructured environments. • Topics included recursive Bayesian estimation, SLAM, sensor fusion, and autonomous control theory. Tenure: Aug 2019 – Dec 2019

• Instructor - North South University

• Digital Signal Processing (EEE 471) | Enrollment: 70 • Designed and conducted MATLAB-based labs for senior undergraduates on FIR filters, convolution and quantization Tenure: Oct 2012 – Aug 2014

• Control System Design (EEE 321) | Enrollment: 100 • Designed and led junior undergraduates through hands-on MATLAB/Simulink labs on LTI control systems • Tenure: Oct 2012 – Aug 2014

• Undergraduate Teaching Assistant - North South University

  • Probability and Statistics (MAT 361) • Instructed senior undergraduates on probability theory, descriptive statistics, hypothesis testing, and statistical inference. Tenure: Jan 2010 – Aug 2012

Skills

• Gen-AI/NLP: GPT4, Llama, Gemini, Claude, FLAN-T5, RAG, Langchain
• Multimodal AI & Signal Modeling: Multimodal signal modeling, behavioral prediction, sensor fusion
• ML Systems: One-shot learning, Siamese networks, contrastive learning, VAE, anomaly detection, inference efficiency
• Frameworks: PyTorch, TensorFlow, Hugging Face, OpenCV
• Data Engineering: ETL, AWS (EC2, S3, Lambda), Vector DB, Git, Docker, MLflow, StreamLit, Gradio, Tableau
• Programming Languages: Python, SQL, R

Publications

• Anik, S.M.H., Allaberdiyev, Y., Afrose, S., Mullick, T. and Karabiber, F., A study on adversarial attacks in Deep Learning-based traffic signal recognition for autonomous vehicles. Future Digital Technologies and Artificial Intelligence, 1(2), pp.8-18 [2025], [Link], [Journal]

• T. Mullick, S. Shaaban, A. Radovic, and A. Doryab, “Framework for Ranking Machine Learning Predictions of Limited, Multimodal, and Longitudinal Behavioral Passive Sensing Data: Combining User-Agnostic and Personalized Modeling,” JMIR AI [2024], [Link], [Journal]

• T. Mullick, A. Radovic, S. Shaaban, and A. Doryab, “Predicting depression in adolescents using mobile and wearable sensors: multimodal machine learning–based exploratory study,” JMIR Formative Research [2022], [Link], [Journal]

• M. Hasan and T. Mullick, “Blockchain and artificial intelligence enabled autonomous smart manufacturing consortium,” IISE, [2021], [Link], [Conference]

• T. Mullick, M. E. Ershad, M. A. Matin, and A. Rahman, “Design of UWB antenna with band-notch at 5 GHz,” LAPC, [2012] [Link] [Conference]

• A. Bonaquist, M. Grehan, O. Haines, J. Keogh, T. Mullick, N. Singh, S. Shaaban, A. Radovic, and A. Doryab, “An automated machine learning pipeline for monitoring and forecasting mobile health data,” IEEE SIEDS [2019] [Link] [Conference]

• T. Mullick, M. Cardei, S. Ahmed, and A. Doryab, “Novel Image Representation of Time Series Sensor Data: Exploratory Analysis to Highlight Differences in Behavior,” [Preprint]

Talks

• Ranking Machine Learning Predictions of Behavioral Passive Sensing Data that is Limited, Multimodal, and Longitudinal in Nature, Commonwealth Cyber Initiative, 2024
• Predicting Depression in Adolescents Using Mobile and Wearable Sensors: Multimodal Machine Learning, Link Lab Research Day, 2023
• Blockchain and Artificial Intelligence Enabled Autonomous Smart Manufacturing Consortium, IIE Annual Conference, 2021

Service and leadership

• CHI - Reviewer (ACM) (2026)
• IMWUT - Reviewer (ACM) (2025) (2021)
• ISWC – Reviewer (ACM) (2025)
• Ranking Association for Advancement of Artificial Intelligence (AAAI) member (2021-2022)
• JMIR Formative Research – Reviewer (2022)