| 20,000+ Fresh Resumes Monthly | |
|
|
| | Click here or scroll down to respond to this candidateCandidate's Name
PHONE NUMBER AVAILABLE EMAIL AVAILABLELINKEDIN LINK AVAILABLE github.com/NDK22 www.Candidate's Name .com SKILLSPython, SQL, PL/SQL, PySpark, Linux, Relational Database, NoSQL Database, Docker, BitBucket, OpenShift, Machine Learning Algorithms, MLFlow, AirFlow, Deep Learning, LLMs, Jira, Time Series Analysis, AWS, Hadoop, Spark, Predictive Analytics, WMS, ETL, MongoDB, Azure, Databricks, Snowflake, Tableau, ERP, CRM, GCP, Advanced Excel (VLOOKUP, Pivot Table), Kubernetes. EXPERIENCEData Science Research Scientist September 2023 - Present UT Arlington Research Institute Fort Worth, TX Spearheaded the development of a golf swing training system using computer vision (OpenCV, OpenGL) and 2 depth cameras. Elevated body key points capture efficiency by 200% through customizing the API for deep analysis and data visualization. Applied Dynamic Movement Primitives (DMPs) to model and analyze 100+ swings; leveraged Dynamic Time Warping (DTW) to quantify similarities and differences, achieving a 40% improvement in swing accuracy metrics. Data Scientist Intern Capstone January 2024 - May 2024 Bank of America Livermore, CA Designed a deep learning model tailored to achieve a recall rate of over 85% in identifying DeepFakes during virtual conferences. Leveraged Generative Adversarial Networks (GANs) to create 500 personalized DeepFake videos, enhancing model robustness. Engineered 3 models (CNN + LSTM, CNN + ResNet, and MTCNN + MesoNet) using TensorFlow, Keras, and PyTorch. Senior Data Analyst December 2016 - August 2022Accenture Mumbai, India Directed over 200 release projects, utilizing advanced data analytics to ensure successful deployment and operational efficiency. Developed and applied predictive models for data center migration, achieving 99% system stability. Enhanced and optimized Oracle Retail Demand Forecasting (RDF) process, improving forecast accuracy by 20%. Optimised 30+ SQL queries, triggers, and procedures, reducing batch job failure rate by 15% and ensuring data accuracy. Enhanced CI/CD pipelines using Jenkins, analyzing deployment data to achieve a 97% success rate. Deployed PL-SQL scripts, Informatica workflows, Oracle Forms and Reports, OpenShift configurations, AutoSys jobs, and event handlers, optimizing data infrastructure and data pipelines through 10-15 weekly Agile iterations. Built an interactive Power BI dashboard to visualize key performance indicators (KPIs), leading to a 40% reduction in defects. Led supply chain data analysis to drive process improvements and strategic growth, contributing to a $50M growth in revenue. Overhauled and maintained databases and data warehouse, including RMS and Teradata, achieving a 20% reduction in downtime. Conducted weekly EPOS (point of sale) transaction audits, resolving 15+ anomalies monthly with root cause analysis (RCA). Implemented Blue Prism (RPA) for end-to-end automation of incident reviews, estimating $100,000 in revenue savings annually. PROJECTS Student Performance Indicator Python, Flask, Scikit-learn, HTML, Bootstrap, AWS Elastic Beanstalk GitHub Predicted students math scores using machine learning techniques. Integrated Flask framework for backend development and HTML CSS for the front end. Enabled continuous deployment using AWS CodePipeline. Cyber Threat Identification Analyser LLMs, OpenAI, LangChain, Vector Database, ChromaDB, Sci-BERT GitHub Directed development of a task-specific Large Language Model for cyber threat identification from reports. Formed data scraping pipeline, boosting model accuracy by 11% through contextualization with ChromaDB. Nikotronics Electronic Product Assistant Chatbot GenAI, LLM, NLP, OpenAI API, Flask, JavaScript, AWS EC2 GitHub Created a Flask-based chatbot using OpenAIs GPT 3.5 to offer instant assistance and product information for electronics. Enabled real-time communication and product information retrieval across 5 - 10 categories for a user-friendly experience. NBA Player Position Classification Python, Scikit-learn, NumPy, Pandas, Matplotlib, Undersampling GitHub Built an SVM model handling imbalanced data with preprocessing and feature engineering. Utilized logistic regression, random forest, AdaBoost, and KNN. Employed GridsearchCV. Achieved 57.19% average accuracy in 10-fold cross-validation. CERTIFICATIONS Google Data Analytics Professional Certificate November 2023 AWS Certified Developer - Associate August 2020EDUCATIONMaster of Data Science, University of Texas at Arlington, GPA 4.00/4.00 August 2022 - May 2024 Relevant Coursework: Probability and Statistics, Data Mining, Machine Learning, Neural Networks, and Bioinformatics. Bachelor of Mechanical Engineering, Vellore Institute of Technology, GPA 3.70/4.00 July 2012 - May 2016 |