Education
======
- PhD in Computer Science, University of Illinois Chicago
- August 2023 – May 2028 (Expected)
- GPA: 4.00 / 4.00
- Relevant Coursework: Machine Learning on Graphs, Causal Inference, Energy Efficient Deep Learning, Algorithmic Fairness and Responsible AI
- BSc in Computer Science and Engineering, Shahjalal University of Science and Technology
- Relevant Coursework: Laplace Transform, Complex Analysis, Analytic Geometry, Calculus, Linear Algebra, Probability and Statistics, Economics, Communication Engineering, Computer Graphics.
Research Experience
======
- Graduate Research Assistant — May 2025 – Present
- University of Illinois Chicago
- Advisor: Professor Elena Zheleva
- Chicago, IL, USA
- Developing scalable machine learning methods for causal discovery, causal inference, and learning from incomplete and high-dimensional data.
- Developed TriOpt, a scalable causal discovery algorithm using causal ordering and Sherman–Morrison rank-one updates, achieving substantial speedups over NOTEARS, GOLEM, and DAGMA on high-dimensional benchmarks.
- Developed SCORE-EM, a causal discovery framework for missing-at-random data combining MALA-based conditional sampling with score-matching-based causal ordering.
- Research on temporal causal discovery, relational causal discovery, graph neural networks, and causal learning from complex observational data.
- Applied causal discovery methods including NOTEARS, DAGMA, PC, FCI, and GES in interdisciplinary research involving microbiome and digital-phenotyping data.
- Graduate Research Assistant — August 2023 – December 2024
- University of Illinois Chicago
- Advisor: Professor Pedram Rooshenas
- Chicago, IL, USA
- Investigated diffusion models and energy-based generative methods for improving optimization and convergence of Physics-Informed Neural Networks (PINNs) for solving partial differential equations.
Professional Experience
======
- Junior Software Engineer — April 2023 – July 2023
- Dynamic Solution Innovators (DSi)
- Dhaka, Bangladesh
- Contributed to backend development of an internet service provider subscription platform using Ruby on Rails.
- Implemented automated invoice PDF generation using the Prawn and Receipts libraries.
Skills
======
Programming Languages
Python, C++, Java, SQL
Machine Learning & AI
PyTorch, PyTorch Geometric, Hugging Face, scikit-learn, NumPy, SciPy, CuPy
Causal Machine Learning
DoWhy, EconML, causal-learn, gCastle, CausalNex
Generative AI & LLMs
Diffusion Models, Variational Autoencoders (VAEs), GANs, Retrieval-Augmented Generation (RAG), Embeddings, Vector Databases, LLM Quantization
Research Areas
Causal Inference, Causal Discovery, Graph Neural Networks, Deep Generative Models, Time-Series Modeling, Physics-Informed Machine Learning
Systems & Compute
Linux, Git, Docker, SLURM/HPC, Google Cloud Platform (GCP), Distributed Training (DDP/FSDP)
Online Course Certificates
- Machine Learning with Python-From Linear Models to Deep Learning, MITx
- Neural Networks and Deep Learning, Deeplearning.ai
- Applied Machine Learning in Python, University of Michigan
- Mathematics for Machine Learning: Linear Algebra, Imperial College, London
- Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization, Deeplearning.ai
- Getting Started with AWS Machine Learning, AWS
- Statistical Thinking in Python, Datacamp
- Time Series Analysis in Python, Datacamp
- Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning, Deeplearning.ai
- Applied Plotting, Charting & Data Representation in Python, University of Michigan
- Computer Vision Basics, Deeplearning.ai
- Data Science Math Skills, Duke University
- Introduction to R, Datacamp