About Shashank Pagidimarri
-
Viewed 360
About me
I am a software developer with a passion for creating innovative and impactful products using Python and R. Currently, I am pursuing a master’s degree in IoT at the University at Buffalo, where I am learning how to design, implement, and optimize smart and connected systems. I have a bachelor’s degree in electronics and communications engineering from Vellore Institute of Technology, where I gained a solid foundation in engineering principles and practices.
Previously, I worked as a software developer at GenInvo, a leading company in the life sciences industry. There, I spearheaded end-to-end product development, from ideation to delivery, using Python and R. I designed intricate backends for document classification, data extraction through machine learning, and complex data transformation and ETL processes. I also executed database design and oversaw CI/CD pipelines for efficient product delivery. I enjoyed working with a talented and diverse team of developers, engineers, and analysts, and I contributed to the company’s culture of innovation, collaboration, and excellence.
Education
-
2022 - 2023
University at Buffalo, The State University of New York
Master’s in Internet of Things,
• Coursework: Deep Learning, Big Data Analytics, Analysis of Algorithms, Pattern Recognition.
-
2013 - 2017
Vellore institute of Technology
Bachelors in Electronics
Experience
-
2019 - 2022
Geninvo
Machine Learning Engineer
• Effectively contributed to three distinct product lines by creating resilient backend frameworks and integrating machine learning
solutions to address tasks such as sentence matching, document parsing, and data mapping.
• Created a robust Named Entity Recognition model using Spacy and Scikit-learn to accurately identify patient names,
personal identifiers, and drug information from clinical trial documents such as Protocols and CSR reports.
• Developed a framework to detect similarities among sentences within multiple documents. By leveraging the capabilities of
natural language processing models like Transformers, fine-tuned on clinical data, achieved an impressive 75% accuracy.
• Created an interactive data visualization dashboard with R-Shiny and Angular for user-friendly data exploration, leveraging
PyTorch-based machine learning models for clinical data insights resulting in a 40% increase in user interaction.
• Streamlined deployment processes by utilizing Docker for containerization and Kubernetes for orchestrating and scaling.
Managed CI/CD pipelines, ensuring continuous integration and deployment. Saved 20+ hours per week in manual
deployment tasks.
• Developed and integrated machine learning models into real-world products by constructing backend APIs using Flask,
resulting in a seamless user experience and improved product performance. Reduced customer support issues by 40%.
• Wrote comprehensive test cases using pytest, adhered to best coding practices, and ensured thorough documentation to
facilitate efficient knowledge transfer within the team, enhancing code reliability and understandability. -
2018 - 2019
| Tvasthaa Data Solutions
Machine Learning Engineer
• Built a text similarity model using Scikit-learn and NLTK, utilizing word embeddings to map columns across different
datasets, resulting in a 30% reduction in data mapping errors.
• Built a Django backend for a document editor app, seamlessly integrating MongoDB for version tracking and Amazon S3
for robust file storage, ensuring efficient data management.
• Played a key role in MLOps by implementing Amazon SageMaker pipelines for deploying text similarity and document
processing ML models. Achieved a 40% reduction in production workflow deployment time.