Resume
Work
Experience
May 2023 - Present
Deep Learning Researcher
In collaboration with Prof. Michael Guerzhoy (University of Toronto) and Dr. Noah Paulson (Argonne National Laboratory) to develop an ML framework for generating novel chemical composites.
-
Successfully implemented variational autoencoder (VAE), generative adversarial networks (GANs), and latent diffusion model (LDM) architectures and Achieved exceptional reconstruction quality with LDM, producing near-identical images.
-
Developed a PyTorch objective function combining neural style transfer and spatial statistics to models’ ability to capture key structural characteristics, generating statistically diverse images with lower mean absolute error compared to previous models.
-
For results, refer to https://github.com/sajjad-git/pytorch_chemical_composite_generation
May 2022 - May 2023
Machine Learning Intern
-
Developed a semi-supervised machine learning algorithm leveraging Integer programming and deep learning (autoencoder) in Python that predicts the number of people in a house from WiFi channel state information (CSI) with 80% accuracy resulting in bringing an additional estimated $2M value to the company.
-
Developed an unsupervised machine learning model that improved motion localization and prediction in a house from WiFi CSI. The improved model employed clustering, integer programming, and Natural Language Processing (NLP-Bag-of-Words) and achieved > 95% accuracy and resulted in bringing $2M value to the company.
-
Applied mixture models, spectral model, and multidimensional scaling from scikit-learn to cluster noisy data resulting in an 80% accuracy score.
-
Developed a hidden markov model algorithm to extract hidden states (number of people in a house) from the noisy house occupancy data using integer programming resulting in an additional 15% improvement.
-
Nov 2021 - May 2022
Machine Learning Intern
-
Implemented a signal segmentation algorithm based on calculating rate of change in signal amplitude in Python which improved segmentation accuracy from 40% to 85%.
-
Implemented a kurtosis analysis algorithm in Python to detect misclassified signals using statistical analysis; improved performance from from 74% to 98%.
Education
2018 - 2023
University of Toronto | Bachelor's Degree
BSc. Industrial Engineering + AI minor
GPA 3.85
Skills
& Expertise
-
Deep Learning Expertise: Proficient in implementing and optimizing deep learning architectures such as VAEs, GANs, and LDMs.
-
PyTorch Proficiency: Developed complex objective functions and neural network models using PyTorch.
-
Python Development: Strong coding skills in Python, enabling the development of efficient and scalable machine learning solutions.
-
Algorithm Development: Demonstrated ability in designing semi-supervised and unsupervised machine learning algorithms for diverse applications.
-
Signal Analysis: Successfully implemented algorithms for signal segmentation and kurtosis analysis to improve data quality and interpretation.
-
Machine Learning in Production: Extensive experience in developing production-ready machine learning models with a focus on reliability and performance.
-
Statistical Analysis: Proficient in using statistical techniques for data analysis and validation, ensuring the accuracy and reliability of AI models.
-
Data Clustering: Applied advanced clustering techniques like mixture models and spectral modeling for data segmentation.
-
Natural Language Processing: Leveraged NLP techniques, such as Bag-of-Words, for unique applications like motion prediction from WiFi CSI.
-
Integer Programming: Skillfully applied integer programming in conjunction with machine learning for predictive modeling.
-
End-to-End Application Development: Experience in creating comprehensive web applications, combining frontend and backend development with AI capabilities.
-
AI Research Collaboration: Collaborated with academic professionals on cutting-edge AI research projects, contributing to the generation of novel solutions and insights.
-
Cloud Platform Experience: Familiar with cloud platforms like AWS and GCP, enabling scalable machine learning deployments.