PhD researcher building deep learning systems that ship.
Nader Lobandi
Ph.D. Student · M.Sc. Data Science
Data Scientist & PhD Researcher
University of Denver
PhD researcher in Computer Science with 4+ years building and deploying production ML systems in industry and academia. Work spans multimodal deep learning, computer vision, model compression and quantization for on-device inference, GPU programming with CUDA, and large-scale data pipelines on Azure and Databricks. Grounded in statistical learning, probabilistic modeling, optimization, and algorithm design. Four peer-reviewed publications and an M.S. in Data Science from Northeastern University. Open to research roles advancing efficient, deployable deep learning systems.
Experiences
Graduate Research Assistant
University of Denver, Ritchie School of Engineering & Computer Science
- ▸Researching model compression, quantization, and hardware-aware optimization for on-device vision and multimodal inference, including GPU programming with CUDA.
- ▸Designing novel computer vision architectures for facial expression recognition trained with soft labels, targeting both ambiguity between overlapping expression classes and demographic bias in model predictions.
- ▸Developing a Digital Twin system for Mild Cognitive Impairment detection using multimodal deep learning, advised by Dr. Mohammad Mahoor.
Data Scientist
BeanSprout AI
- ▸Built a cardiovascular risk prediction model using LightGBM and XGBoost, reaching AUC 0.89, and took it from data ingestion through hyperparameter tuning to deployment on Modal with MLflow tracking.
- ▸Implemented real-time speech interaction using Vertex AI speech-to-text and text-to-speech, and designed agentic workflows for secure document access and intent routing on an elder-care platform.
- ▸Engineered a RAG pipeline over patient documents with persistent chatbot memory and user accounts, removing repeated manual data lookups from each session.
Data Scientist
VHB (Vanasse Hangen Brustlin Inc.)
- ▸Analyzed terabytes of city-scale traffic data using PySpark, SQL, and Delta Live Tables on Databricks, and audited streaming feeds to find that over 70% of the data came from a single unreliable vendor.
- ▸Deployed an internal RAG chatbot with SQL execution, giving project managers natural-language access to employee hours, assignments, and reporting data that previously took days to pull manually.
- ▸Built a real-time object detection and tracking pipeline using YOLO and Azure Vision to analyze live intersection feeds and flag near-miss incidents, optimizing inference latency to keep up with streaming video.
- ▸Developed LSTM, Prophet, and SARIMA time-series models to forecast energy demand for NY Transit Authority, improving load-prediction accuracy to support peak-reduction strategies.
Data Scientist Co-op
Kibur Medical Inc.
- ▸Built a bilateral filtering preprocessing pipeline for high-dimensional biomedical images, improving cell quantification accuracy by roughly 20%.
- ▸Integrated AWS S3 for scalable, real-time image retrieval, replacing local storage and supporting a continuous clinical imaging data workflow.
Research Scientist
Northeastern University
- ▸Trained and evaluated LSTM, Gaussian mixture, and regression models on time-series sensor data for COVID-19 detection, reaching 95% recall under noisy measurement conditions. Built training pipelines in PyTorch.
- ▸Applied detection theory, including MAP, Bayesian, Neyman-Pearson, and Minimax estimators, to separate true sensor response from background noise in low signal-to-noise biosensor measurements.
- ▸Published 4 peer-reviewed papers in IEEE Sensors Letters, Biosensors and Bioelectronics, IEEE CICC, and Journal of Applied Physics.
Education
Ph.D. in Computer Science
University of Denver, Ritchie School of Engineering & Computer Science
FocusMultimodal Deep Learning, Computer Vision, Efficient Foundation Models, Model Compression & Quantization, On-Device Inference, GPU Computing & CUDA Programming
GPA4.0HonorsIAAP 2026 Scholarship Award
M.Sc. in Data Science
Northeastern University, Khoury College of Computer Sciences
HonorsGordon Institute LEADERS Fellowship; LEADERS Leadership Certificate
B.Sc. in Electrical Engineering
Sharif University of Technology
HonorsNational Physics Olympiad Silver Medal; Ranked top 0.1% out of 100,000+ applicants in national university entrance exam
Publications
4 peer-reviewed papers · IEEE · Biosensors & Bioelectronics · AIP Publishing
P. Sadeghi, N. Lobandi, R. Alshawabkeh, A. Rui, W. Sun, J. Chen
R. Burns, A. Wiechmann, P. Sadeghi, N. Lobandi, N. Fathy, R. Huang, N. X. Sun, et al.
X. Shi, P. Sadeghi, N. Lobandi, S. Emam, S. M. S. Abrishami, I. Martos-Repath, et al.
A. R. Will-Cole, A. E. Hassanien, S. D. Calisgan, M. G. Jeong, X. Liang, S. Kang, ..., N. Lobandi, M. Rinaldi, S. Gong, N. X. Sun
Projects
JobScout — Agentic Job Search System
Built a multi-agent job search tool where an orchestrator dispatches specialist sub-agents for search, scoring, and drafting, each scoped to one task through its own agent skill. Wrote a custom MCP server normalizing eleven job boards behind a single tool surface. Kept dealbreaker filtering in deterministic Python so an untrusted posting cannot prompt-inject past it, and enforced a human-in-the-loop gate with no code path to auto-submit.
SecureFaceID — Liveness-Aware Face Authentication
Built a face authentication system with liveness detection that runs on a standard RGB camera instead of depth or infrared hardware. Uses blink detection to reject photo and screen spoofing attempts, and stays accurate when the user is wearing a mask.
E-Waste Sustainability Assistant
Built a vision tool that identifies electronic waste from a photo and returns its carbon footprint, recoverable value, and disposal action. Implemented a decision pipeline pairing a vision model with a heuristic engine and safety overrides, backed by a sourced knowledge base for every figure it reports.
Financial News Sentiment Analysis
Built an NLP system to classify sentiment in high-volume financial news. Benchmarked classical and transformer models across two datasets, with FinBERT at 0.73 accuracy and 0.74 macro-F1 on Alpha Vantage, and BERT-uncased at 0.86 and 0.86 on Yahoo Finance, validated against real ticker movements.
Financial Time-Series & Document QA
Built a Streamlit tool for interactive backtesting of forecasting strategies with reliable horizons up to two months, paired with a chat interface for querying 10-K filings in plain language.
Personal Finance Web App
Built a self-hosted budgeting and expense tracker as a full-stack Flask application with a MySQL backend, including schema design for transactional data, automated alerts for suspicious transactions, and multi-user authentication.
Skills
By Domain
Deep Learning & Computer Vision
95%AI & Agentic Systems
90%Data & ML Engineering
85%Statistical Modeling
85%Proficient
Building Toward
Contact
PhD researcher at the University of Denver working on multimodal deep learning, computer vision, and efficient models that run on real hardware. I have spent 4+ years shipping production ML systems alongside the research. Open to collaboration and research opportunities in deep learning, computer vision, and applied AI. If you are a builder or thinker working on hard problems, let's connect.
Ph.D. Student · M.Sc. Data Science · University of Denver