Data Science Research collaborator

• Oct 2023 - Present

Graduate Research Assistant

• Jan 2023 - Present

As an ML Research Assistant at the Amal Precision Medicine Lab at Northeastern University. The Lab's research involves using Artificial Intelligence and Multimodal data for improving cardiovascular disease care including personalized treatment recommendation. I was responsible for developing machine learning models to analyze large sets of biological and clinical data, including genomics, proteomics, metabolomics, and electronic health records (EHRs), to better understand the underlying causes of cardiovascular disease. I worked closely with senior researchers to design experiments that used machine learning to identify biomarkers, predict disease progression, and evaluate treatment effectiveness. I was also responsible for analyzing data using a range of machine learning techniques, including deep learning, random forests, and gradient boosting, to develop predictive models and gain insights into disease mechanisms. through this opportunity I collaborated with other researchers in the lab to integrate machine learning with other approaches to advance precision medicine for cardiovascular disease. Show less

AI/ML Engineer Intern

• May 2023 - Aug 2023

As a Machine Learning Engineer Intern at AstraZeneca, I played a pivotal role in the Drug Formulation and Dosage Design team by spearheading a groundbreaking project. My primary task involved the creation of a robust Extract, Transform, Load (ETL) pipeline tailored to pharmaceutical data needs. Leveraging advanced technologies such as Apache Spark and Python, I designed the pipeline to streamline data processing, significantly reducing manual efforts and mitigating the risk of human error. What set our ETL pipeline apart was the integration of Natural Language Processing (NLP). I employed sophisticated NLP techniques using libraries like spaCy and NLTK to enable contextual extraction from unstructured data sources like research papers, PowerPoint presentations and instruments. This innovation added a layer of intelligence to our system, allowing it to grasp contextual information effectively. With the contextual extraction capabilities, our team gained deeper insights, accelerating drug formulation and dosage design research. This project held the potential to expedite the development of life-saving pharmaceuticals. The technologies and tools I used during this internship included Apache Spark, Python for NLP, custom-built machine learning models, and data warehousing solutions. This experience at AstraZeneca reinforced my commitment to data-driven solutions in the pharmaceutical industry. I am enthusiastic about continuing to apply my skills and expertise in data engineering, NLP, and machine learning to drive innovation in the field of data science. Show less

Machine Learning Engineer Co-op

• Sep 2022 - Jan 2023

As a Machine Learning Engineer at Omdena, I led the development of advanced algorithms using Tensorflow for the analysis of geospatial data to create AI-assisted web mapping products. In this role, I designed the data flow and prototyped the algorithms, and played a key role in deploying the machine learning models. One of my primary responsibilities was to import data from S3 buckets to Data Wrangler and transform the data to ensure that it was in the right format for use in machine learning models. This process improved the accuracy of predictions, enabling the team to provide better recommendations and insights to customers. In addition to my technical work, I collaborated closely with cross-functional teams, including product management and design, to ensure that the machine learning solutions aligned with the company's overall product vision. Through my contributions, the team was able to deliver highly effective and innovative products that met customer needs and exceeded expectations. Show less

Data Scientist

• Jun 2022 - Sep 2022

At Ascend Learning, I utilized Snowflake to design a data flow that facilitated the analysis of their data, allowing the team to gain valuable insights into the most in-demand products and improving overall sales. Additionally, I performed sentiment analysis by labeling data, giving the business a better understanding of how customers felt about their products. To improve customer spending predictions, I created Linear regression models using scikit-learn and helped the team build an RFM analysis. Furthermore, I developed a Ridgeclassifier model to classify customers into two groups based on their purchasing consistency. This enabled the marketing team to focus their efforts on customers who were not consistent in their purchases. I also conducted hyperparameter tuning and tracking on models using W&B, which not only provided the team with a better understanding of model performance but also helped reduce computation time and training costs for new models. Show less

Data Engineer fellow

• Mar 2022 - Sep 2022

Throughout the Fellowship program, I was responsible for developing ETL pipelines to process, develop and test models using big data in the cloud. I leveraged technologies such as Apache Spark and Hadoop to process large volumes of data efficiently. I designed and implemented a relational database using AWS RDS to help analyze data effectively, which improved the performance of the data processing pipeline. To improve the development process, I developed and implemented a CI/CD system using Git and Jenkins, which allowed for faster and more reliable deployment of new code changes. Additionally, I attended leadership and networking workshops which helped me improve my oral and written communication skills, enabling me to collaborate more effectively with cross-functional teams. To ensure proper documentation and knowledge transfer, I developed and maintained detailed technical documentation throughout the project, which aided in troubleshooting and reduced the learning curve for new team members. Show less

Undergradudate bioinformatics research assistant

• Apr 2021 - Feb 2022

As an Undergraduate Bioinformatics Researcher at Kstate Bioinformatics Center from January 2021 to May 2022, I conducted a comprehensive quality assessment of the genome of Zophobas atratus, a tenebrionid beetle, using the Blob Tools 2 pipeline developed by Sanger Institute. The analysis involved mapping the raw reads to the genome assembly, identifying potential contaminants using Kraken2, and using BUSCO to assess the completeness of the genome. Based on the BUSCO analysis, the genome was found to be 91.8% complete. I was responsible for identifying and removing genomic scaffolds that represented contamination from Chordata, Nematoda, and Porifera. To facilitate data preprocessing, analysis, and visualization, I developed custom scripts using Python, Bash, and R. Additionally, I was part of a comparative genetic study at the KSU Bioinformatics Center that obtained newly sequenced genomes of several tenebrionid beetles for analysis. In recognition of my contributions, I was awarded the K-INBRE award for excellence in undergraduate bioinformatics research. Show less