CV

Education

• M.S. in Computer Science, University of Colorado Boulder, USA, 2025
• B.Tech. in Electronics and Communications Engineering, PES University, India, 2021

Work experience

• Web Developer : June 2024 – Aug 2024
  • Developed CU Boulder research labs web pages using Jekyll, Ruby, CSS and JavaScript and deployed on custom domains.
  • Automated 80% of website’s content generation using Ruby and Python.
  • Managed continuous integration and deployment (CI/CD) pipelines using GitHub Actions.
• Senior Software Engineer: Sandvine Technologies : Apr 2023 - July 2023
  • Optimized Sandvine’s products’ server load prediction tool website’s page response time by 70% by improving the backend algorithm performance from O(n3) to O(n) via dynamic programming and caching data. [Python, Django ORM]
  • Designed postgres schemas to store frequently accessed API data reducing the website’s page response time by 90%
  • Developed query optimization techniques using data partitioning, indexing and filtering to achieve 50% improvement in the time to extract the data from the database.
  • Built an automated testing framework for more than 50 features integrated in the prediction tool website reducing two days of manpower needed on a monthly basis. Enhanced the existing unit tests and functional tests to cover up to 80% of the codebase.
  • Led the technical staff for customer related issues in the enterprise solutions for all Sandvine’s 4G and 5G control plane products.
• Software Engineer: Sandvine Technologies : Oct 2022 - Mar 2023
  • Analyzed and managed production services (using Kubernetes and Docker) for the prediction website tool. This was used by all of Sandvine’s customers during their onboarding process including the leading telecommunication companies.
  • Implemented schema migration in postgres to manage schema changes overtime during production deployment.
  • Gained excellence in data modeling, improved accuracy of regression models from 90% to 98% by optimizing the model hyperparameters. These were used to train data models to predict total Sandvine’s telecom products. Training involved complex datasets with more than 10 varying parameters on average. [Python, Statistical modeling, Matplotlib, Git]
  • Led as Scrum Master, Escape Defect Analysis (EDA) meetings, and ensured on-time delivery, discussed and implemented bug prevention strategies, reducing bug frequency by 80% in three months.
  • Developed a Deep Learning model to reduce time spent in data modeling from 3 days to under 30 minutes, leading to a significant enhancement in feature delivery from 6 to 10 features per month. Also, served as the Scrum master for the team.
  • Developed and documented around 10 new features within the categories of ‘Ease of Usability’, ‘Adaptability to Multiple Configuration’, and ‘Performance Improvement’ for both frontend and backend sections of the application.
• Test Engineer: Sandvine Technologies : Jun 2021 - Sept 2022
  • Enhanced a Django web app with PostgreSQL for the database and Vue.js for the UI to predict server load estimates. Explored REST APIs, tested with Selenium/Postman, and increased Django code coverage from 40% to 60% through rigorous unit testing.
  • Analyzed system CPU performance of Sandvine’s products and employed data modeling to predict server CPU load estimates with 90% accuracy. Managed data collection, preprocessing, and evaluation using Statistics and Pandas.

Skills

• Languages & Database
  • Python
  • C++
  • HTML
  • CSS
  • Javascript
  • Reactjs
  • Vuejs
  • PostgreSQL
  • SQLite
• Framework & Tools
  • Django
  • Flask
  • Django
  • Kubernetes
  • Tensorflow
  • Pytorch
  • Keras
  • Github
  • Google Colab
  • Jira
  • Github Pages
  • Jekyll
  • Github Actions
• Cloud
  • Google Cloud Platform
  • Amazon Web Service(AWS)
• Technologies
  • Data Structures & Algorithms
  • RESTful APIs
  • Machine Learning
  • Deep Learning
  • Computer Vision
  • Natural Language Processing
  • Software Develpoment
  • Agile

Publications

Pictorial Information Retrieval from EEG using Generative Adversarial Networks

K. Nagarajan, A. Umadi, N. Belur Keshav and N. Krupa, "Pictorial Information Retrieval from EEG using Generative Adversarial Networks," 2022 7th International Conference on Intelligent Informatics and Biomedical Science (ICIIBMS), Nara, Japan, 2022, pp. 269-275, doi: 10.1109/ICIIBMS55689.2022.9971471. keywords: {Visualization;Image color analysis;Convolution;Predictive models;Brain modeling;Feature extraction;Generative adversarial networks;EEG;Image reconstruction;Deep Learning;Brain Media;Generative adversarial networks(GANs)},

Automated Segmentation of Overlapping Cells in Cervical Cytology Images Using Deep Learning

A. Umadi, K. Nagarajan, J. B. Venkatesha, A. Ganesh and K. George, "Automated Segmentation of Overlapping Cells in Cervical Cytology Images Using Deep Learning," 2020 IEEE 17th India Council International Conference (INDICON), New Delhi, India, 2020, pp. 1-7, doi: 10.1109/INDICON49873.2020.9342328. keywords: {Deep learning;Image segmentation;Visualization;Technological innovation;Shape;Conferences;Hardware;Overlapping cell segmentation;cervix cytology;K-means;U-Net},

Service and leadership

• Gradual Professional Development Club (GPDC) Vice Chair in the Computer Science department at the University of Colorado Boulder. (Aug 2024 - May 2025)