About Me
Experienced Data Engineer with over 2 years of industry expertise, specializing in leveraging data-driven insights to drive business decisions and optimize processes. Skilled in data engineering, machine learning, and advanced programming, with a proven track record of delivering actionable solutions and driving innovation in diverse domains.
What I'm Doing
-
ML & AI Development
Advanced ML models crafted to solve complex business challenges.
-
Big Data Engineering
Scalable data architectures and pipelines to harness insights.
-
Data Science & Business Intelligence
Comprehensive analytics to drive impactful decisions-making.
-
Project Management & Leadership
Project leadership and cross-functional team management.
Certifications
DataProfiler-kit : Open-source Python Library
A Python library that provides quick and insightful data profiling for pandas DataFrames. It generates detailed reports including missing values analysis, data type information, correlations, outliers, and column statistics in a clear, organized format.
View project →
Real-Time Weather Data Pipeline
Airflow
Kafka
Spark
Postgres
Python
Docker
Developed a data pipeline that streams, processes, and stores real-time weather data for multiple cities using Apache Kafka, Spark, and Airflow, storing results in PostgreSQL for analysis.
View project →
Real-Time Stock Market Analytics Pipeline
Python
Kafka
EC2
S3
AWS Glue
Athena
Built a real-time stock market analytics pipeline utilizing Kafka for data streaming. Integrated Python along with AWS services such as EC2, Glue, and Athena for deployment, querying, and market analysis.
View project →
Sentiment Analysis with MLFlow
Python
MLFlow
MLOps
NLTK
Scikit-learn
Pandas
Kagglehub
Employed MLflow for Sentiment Analysis on a Twitter Kaggle dataset using SVC, Logistic Regression, and BNB models. Integrated NLTK for text preprocessing and Scikit-learn for modeling, ensuring efficient experiment tracking and model management.
View project →
Advanced Geoanalytical System
Python
AWS
ArcGIS
QGIS
Docker
Big Data
Orchestrated spatiotemporal data ingestion from IoT sensors and mobile SDKs, implementing an advanced geospatial analytical workflow.
View project →
Automated Parcel Delineation
Python
PyTorch
CNNs
UNet
ArcGIS
Utilized computer vision techniques and image segmentation to automate parcel delineation on satellite imagery, enabling more precise cadastral analysis for urban planning and land management.
View project →
Radar Data Integration
Python
Flask
MySQL
ETLs
Power BI
Developed and deployed ETL processes to seamlessly load data from a radar system into a centralized database. Built an analytical system featuring real-time performance visualization of athletes and generating insightful reports.
View project →
DialoGPT Chatbot
Python
Flask
HuggingFace
BART
DialoGPT
GCP
Developed an AI-driven chat companion with voice integration.
View project →