Research Assistant Data Science

SHARINI JAYABAL

**********@*****.*** https://www.linkedin.com/in/sharini-jayabal/ Sharini-19 (github.com) Ph: 682-***-**** EDUCATION

University of Texas at Arlington, Texas Aug 2024

Master of Science: Computer & Information Science (Data Science) Easwari Engineering College, Chennai, India Apr 2022 Bachelor of Technology: Information Technology

SKILLS

Big data & Cloud : AWS, GCP, Azure (AutoML, Databricks), Spark, Hadoop, Kafka Programming : Python, R, HTML, CSS, Java, C#, MATLAB, Golang Data Engineering : SQL, Snowflake, HQL, Postgres, NoSQL Tools : Git, GitHub, Power BI, Tableau, ERP, JIRA, Agile Data skills : ETL, Unit tests, Data Quality (Pylint/Flake8/Pre-commit), SonarQube Analysis EXPERIENCE

Research Assistant at UTARI #ImageProcessing #MachineLearning #AI #ComputerVision Jan’23 – Aug’23

• Built a feral hog detection model to help North Texas farmers to prevent appr. $2.5 B crop damage every year.

• Automated end-to-end Machine Learning model deployment with CI/CD integration (Cloud build).

• Built a secured Fast API end point to upload unstructured video files to GCS to be picked up by a deep learning model to perform close to real-time drone (Unmanned Aerial Vehicle) detection for the US Air Force.

• Developed an Airflow DAG to pick images on a schedule at a golf club for precise golf pose correction by capturing body posture data which will be sent to the GCS storage bucket (Human motion tracking).

• An API endpoint which uses MediaPipe & Deep Learning gives feedback to the players on posture & swing mechanics. Research Assistant at University of Texas, Arlington #VersionControl #DataPipeline Aug’22 – Dec’22

• Worked under the Industrial & systems Engineering department to develop repositories and manage data for research.

• Built a Pipeline for end-to-end data transfer from snowflake to big query using GCP cloud function with pre-processing, feature engineering/selection. Used Pub/sub & gcloud scheduler to setup triggers.

• Performed Clustering & statistical analysis to find factors leading to risky sexual behavior risks using health care data. PROJECTS

Market Basket Analysis, #Transactional Data Analysis #Apriori Algorithm

• Analyzed transactional data to uncover associations and relationships between products purchased together.

• Implemented Apriori Algorithm to identify frequent item-sets & association rules for cross-selling and upselling strategies. NLP Speech Emotion Recognition for Autism children, #Social media data #NLP #HPC

• Built a ResNet-based neural network for audio classification and to predict emotions in autism children. HPC clusters were utilized for parallelized model training and computation. Advanced Distributed Search Algorithm, #Docker Deployment #Distributed System

• Engineered a robust distributed system using Go and Python for image retrieval from servers, encapsulated within Docker containers, enabling keyword-driven searches with immediate feedback run on multiple test cases. Lending Club – Loan Default Prediction, #Predictive modeling #Algorithms #PowerBI

• Extracted, Pre-processed, and manipulated raw data (feature engineering) from Lending club website. Built Predictive Models like Logistic Elastic net, Random Forest & SVM using Py libraries like SciPy, NumPy etc.

• Created a user-friendly Power BI dashboard to check Loan default status. CERTIFICATIONS

Google Data Analytics certification Computer Vision and Image tools certification Machine Learning Certification (Coursera)

Contact this candidate