Md Muhtasim Billah

Md Muhtasim Billah

Data Scientist | PhD Candidate, Mechanical Engineering | MS, Statistics

Washington State University

Biography

Welcome to my personal website which serves to showcase my portfolio. I am currently a PhD candidate in the School of Mechanical and Materials Engineering (MME) at Washington State University (WSU), Pullman. My expected graduation date is Summer 2023. I completed my Master’s Degree in Statistics from WSU in Fall 2022. I am actively looking for full time positions in Data Science, Machine Learning or similar roles.

My PhD research has been initially focused on implementing a Monte Carlo based probabilistic model in C++ and Fortran for studying bioparticle transport across blood-brain barrier (BBB). Lately, I have been working on utilizing physics informed neural networks (PINNs) for solving inverse heat transfer problems. I have also studied complex polymer/solvent/nonsolvent systems for industrial applications using molecular dynamics simulations.

Pursuing MS in Statistics has fueled my interest in exploring the expansive world of machine learning and data science to decipher intriguing, real-life problems.

Interests

  • Data Science
  • Machine Learning
  • Stochastic Modeling
  • Scientific Computing

Education

  • PhD in Mechanical Engineering, Summer 2023

    Washington State University

  • MS in Statistics, 2022

    Washington State University

  • BSc in Mechanical Engineering, 2017

    Bangladesh University of Engineering and Technology

Skills

Python

R

SQL

Machine Learning

Big Data

Statistics

Experience

 
 
 
 
 

Data Science Intern

Paylocity

May 2022 – Aug 2022 Schaumberg, IL

The amazing, 12 weeks long, remote internship experience is summarized below.

  • Worked within Agile software development environment by utilizing CI/CD tools and best practices.

  • Incorporated new NLP functionalities (text summarization and emotion detection) to the existing codebase and wrote necessary code for unit testing and model benchmarking against relevant metrics.

  • Contributed towards building a REST API (with FastAPI) having different NLP endpoints hosted by multiple AWS services such as S3, ECR, Lambda and API Gateway (using Pulumi IAC). Tested the endpoints in Postman and deployed to dev using Octopus Deploy.

  • Worked on several other ongoing projects in the Data Science team to facilitate easier implementation by other organizations across the company. In the process, acquired hands on experience with Docker, Spark clusters in Databricks notebooks, Azure services such as DataLake, DevOps and ADF.

 
 
 
 
 

Research Assistant

Washington State University

Aug 2018 – Present Pullman, Washington

Current research is focused on the following.

  • Used finite volume method (FVM) for solving an inverse heat transfer problem using Bayesian Inference machine learning technique.

  • Customized loss functions to deploy physics informed neural networks for complex unsteady, multi-dimensional heat transfer problems.

  • Developed and further improved a probabilistic model based on Monte Carlo method written in C++ and Fortran programming language.

  • Utilized the stochastic model for studying key parameters for drug delivery through blood brain barrier (BBB) as an aid for neurodegenerative diseases such as Alzheimer’s and Parkinson’s.

  • Studied design parameters and relevant characteristic properties for manufacturing functional nanoparticle for drug delivery.

  • Investigated complex polymer/solvent/nonsolvent systems for industrial applications using atomistic models and molecular dynamics simulations.

 
 
 
 
 

Teaching Assistant

Washington State University

Aug 2018 – Present Pullman, Washington

Assisted the instructor with preparing course materials, conducting the class and grading homework as well as exams. Guided students with in-class performance and homework.

  • ME 301 : Thermodynamics (Fall 2018).
  • ME 303 : Fluid Mechanics (Spring 2019).
  • ME 304 : Heat Transfer (Fall 2019, Fall 2022).
  • ME 306 : Thermal and Fluids Laboratory (Spring 2022, Fall 2022).

Accomplish­ments

Top 8% (bronze medal), Kaggle Jane Street Market Prediction

Kaggle / Jane Street Aug 2021
Predictive modeling of trading decisions to maximize the return based on real global stock exchange data.

Data Scientist with Python

DataCamp Apr 2021
Completed a 23 course series that focused on the widely used machine learning algorithms and data science techniques in Python.
See certificate

Top 9% (bronze medal), Kaggle Mechanism of Action (MoA) Detection

Kaggle / MoA Nov 2020
Aimed at solving a multi-lable classification problem to predict mechanism of action (MoA) for new drugs.

Deep Learning Specialization

Coursera Oct 2020
This specialization consisted of five courses on deep neural networks: Neural Networks and Deep Learning, Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization, Structuring Machine Learning Projects, Convolutional Neural Networks and Sequence Models.
See certificate

Machine Learning

Coursera Jul 2020
An in-depth look into the common supervised and unsupervised machine learning algorithms including regression, classification, recommender systems and anomaly detection.
See certificate

Python Programming

DataCamp May 2020
Learned the fundamentals of Python that included the basic data types and structures, utilizing the built in and user defined functions.
See certificate