Hi there! I'm

Sai Shreya Kumar

Data Science and Software Engineering Enthusiast

About Me

I am a master’s student in Computer Science at the University of Illinois - Urbana-Champaign, specializing in Machine Learning and Data Science. I have extensive experience in software development, cloud computing, and deploying scalable machine learning solutions. Skills:
  • Python, C++, C#, Java, JavaScript, R
  • TensorFlow, Keras, PyTorch, Scikit-learn, NLP
  • Microsoft Azure, Docker, Kubernetes, SQL, MongoDB, PostgreSQL
  • ETL Pipelines, Apache Airflow, Tableau, Power BI

Professional Experience

Data Science Intern - K1X, Inc
June 2024 - Present
  • Developed a tax form variant detection feature, improving accuracy and processing efficiency by 30%, leveraging Microsoft Azure for scalable cloud storage and Azure Functions for serverless compute.
  • Built the K1X Aggregator using Python, Scikit-learn, TensorFlow, and Keras, integrating ML models for tax form classification and automated data ingestion using ETL pipelines with Apache Airflow.
  • Created and maintained data visualization dashboards using Tableau and Power BI, improving data accessibility and enhancing decision-making.
  • Collaborated with cross-functional teams to streamline the machine learning models’ deployment in the cloud using Docker and Kubernetes.
Machine Learning Engineer - University of Illinois Urbana-Champaign
January 2024 - May 2024
  • Fine-tuned LLMs and RNNs (LSTM, GRU, ConvLSTM) using TensorFlow and PyTorch, improving streamflow prediction accuracy by 25%.
  • Collaborated with Meta, Uber, and Microsoft to deploy scalable ML models using Apache Spark and GPU acceleration, enabling real-time analysis for water management systems.
  • Migrated the LSPC watershed system to a high-performance .NET console application, integrating ML-driven optimizations such as adaptive learning rates, dynamic resource allocation, and parallel data processing.
  • Designed and implemented cloud-based solutions for handling large datasets, improving data throughput by 20% using scalable APIs.
Data Science Intern - Tenacitics
October 2021 - February 2022
  • Developed interactive data visualization dashboards using JavaScript, Django, Plotly, and Grid-stack.js, improving data accessibility by 30%.
  • Designed and implemented custom machine learning models using Python, Pandas, and Scikit-learn to identify trends, resulting in a 10% increase in customer satisfaction.
  • Integrated PostgreSQL for real-time data retrieval and APIs for enhanced performance and security.
  • Optimized the backend for high-traffic scenarios, improving the system’s overall performance by 15%.
Software Developer Intern - Shivanjali
May 2021 - July 2021
  • Created an in-house UI library to improve reusability by 30%, using React.js for the front-end.
  • Developed and deployed scalable backend systems using Node.js and Express, integrating RESTful APIs to improve data flow between front-end and back-end.
  • Led a team to enhance the platform’s user experience, increasing engagement by 15%.
  • Implemented automated testing and CI/CD pipelines, reducing deployment times by 25%.

Education

2023 - 2025
Master's in Computer Science
University of Illinois Urbana-Champaign
GPA: 3.94/4

Coursework: Applied Machine Learning, Database Systems, Data Mining Principles, Advanced Information Retrieval, Computer Security, Advanced Competitive Algorithm Programming. Extracurricular Activities:

  • Graduate Research Assistant: Migrated the LSPC watershed modeling system to a high-performance .NET console application, improving scalability and computational efficiency.
  • Led architectural transitions and implemented ML optimizations for hydrology and sediment simulation modules.
  • Collaborated on research projects focused on the integration of ML models in water quality simulations.
  • Selected for the Amazon ML Summer School.
  • Participated in university research on Large Language Models (LLMs).
2019 - 2023
Bachelor's in Computer Science
SRM Institute of Science and Technology
GPA: 4/4

Coursework: Artificial Intelligence, Machine Learning, Data Structures, Algorithms, Cloud Computing, Big Data Analytics, Computer Networks, Operating Systems. Extracurricular Activities:

  • Awarded the Best All Rounder for the 2019-2023 batch.
  • Organized a Full Stack Web Development Workshop on behalf of the Design and Innovation (DI) Club.
  • Organized and conducted a 24-hour Hackathon “HackFest2k23” for college students.
  • Organized EduCodathon for school students on behalf of DI Club.
  • Undertook the TCEDS Diploma in Python and received 91%.
  • Full Stack Web Development Certification of 55 hours from Udemy.
  • Helped in developing the IRCICD'22 website for the department and the college.
  • Won the Special Recognition Award in the Rotaract Club of Guindy for being Chairperson of the “Say Yes to Yoga” event.

Projects

NoteScribe
NoteScribe
Developed an AI-driven note-taking application using Flask, Azure, and OpenAI Whisper, enabling real-time transcription and summarization from audio files.
Agentic LLM Framework
Agentic LLM Framework
Built an agentic framework for real-time healthcare automation using PyTorch, integrating Large Language Models (LLMs) for decision-making.
A.T.A.C - A Tech Against COVID
A.T.A.C - A Tech Against COVID
Led the development of a healthcare application using Google Cloud and TensorFlow, reducing report processing time by 40% through real-time ML model integration.

Achievements

President, Design and Innovation Club
Led the club in organizing workshops on AI and full-stack development for over 200 students.
Best All Rounder (Batch 2019-2023)
Awarded the Best All Rounder of the 2019-2023 batch at SRM Institute of Science and Technology.
National Hackathon Winner
Won the Best All-Girls Team Award in HackWIE and HackNITR 2.0 (2020, 2021), National Level Hackathons.

Get in Touch

Feel free to reach out via email or connect with me on LinkedIn!