Computer Science Data Engineer

SREEJA BALNE

+1-813-***-**** **********@*****.*** LinkedIn

EDUCATION

University of South Florida (USF) Tampa, FL Aug 2022 - May 2024 Master’s in computer science. GPA 3.83

Kakatiya Institute of Technology and Science (KITSW) Warangal, TG Aug 2018 - May 2022 Bachelor of Technology (Computer Science and Engineering) GPA 9.38 TECHNICAL SKILLS

• Programming: Python, SQL, PL/SQL, C, Java

• Database Tools: Hadoop, Apache Kafka, Apache Spark, Apache Airflow, Informatica, MongoDB, NoSQL, MySQL, Snowflakes

• Libraries and Frameworks: PyTorch, TensorFlow, Scikit-Learn, Hugging Face, Keras, OpenCV, Pandas, NumPy, Seaborn.

• AI/ML: Supervised and Unsupervised ML, Deep Learning, NLP, LLMs, Statistics

• Tools: AWS (lambda, S3, EC2), AWS Sage maker, Power BI, Tableau, Azure, GCP, Docker, Cloud Computing

• Others: SAS, Jira, Scrum, Test case design

WORK EXPERIENCE

Data Engineer Intern Aakruthi Solutions, India Aug 2021 – Jun 2022

• Performed gap analysis with data sources acquiring 95% accuracy. Built data Pipelines, implemented code modularization involving package creation.

• Implemented optimization algorithms like gradient descent and simulated annealing to finetune model parameters and enhanced model performance to 89%

• Supported super users and business users on reports/dashboards to visualize audit progress, presenting insights on resource shortages to leadership.

• Implemented star and snowflake schemas, coordinating with offshore teams to mitigate production issues.

• Communicated with technical and non-technical audiences about data infrastructure and enhancements in data warehousing.

Data Analyst and AIML Intern Ekasila educational Society, India Jan 2021 – May 2021

• Evaluated business requirements and processes through client interviews, feedback, and workflow analysis

• Improved data retrieval efficiency, reducing ETL job processing time by 70% through SQL query optimization and process improvement.

• Used knime to generate a master server/database listing.

• Leveraged Hadoop for data warehousing, Big Query for data partitioning and clustering, and Sqoop for data movement to optimize processes and cost efficiencies.

• Derived recommendations for software engineers from user feedback, reducing issue reports by 33%.

• Used Locality sensitive Hashing (LSH) for similarity search and duplicate detection improving user rating to 90%. Research Assistant KITSW CSE, India Aug 2020- Dec 2021

• Involved in Customer Analysis Project, identifying potential customer groups through K-Means clustering.

• Utilized Power BI for effective data visualizations, conveying complex findings to stakeholders.

• Implemented an OCR and Python-based automation system, reducing document processing and data analysis time by 70%. ACADEMIC PROJECTS

Prediction of Diabetes at early stages using ANN & Outlier Exposure

• As Lead for team of eight to develop a machine learning model for early diabetes detection. Conducted in-depth data analysis, implemented data preprocessing techniques, and built a PyTorch-based ANN model. Achieved a 2.7% accuracy improvement through rigorous testing and outlier detection. Dynamic Scheduling for Fog Computing Environments RNN, A3C, Edge cloud, Optimized DD Q-Learning based RL.

• Optimized cloud resource utilization by developing a client usage analysis system. Implemented load and stress testing to identify performance bottlenecks. Reduced cloud costs by 2.3% through strategic resource allocation. Automatic license plate detection using KNN.

• Built real-time recognition and character extraction from vehicle data, integrating Oracle and MySQL into HDFS via SQOOP. Explored automation opportunities to improve testing efficiency and achieving 89.4% efficiency in recognizing license plate numbers.

CERTIFICATIONS

• AWS Certified Cloud Practitioner Link

• AWS Certified Developers Associate Link

• Database design and programming with SQL (ORACLE) Link

• CISCO Data Science Link

Contact this candidate