Data Engineer • Cloud Analytics Professional • Tech Enthusiast
- 🎓 Currently pursuing a Master's in Information Systems at Northeastern University.
- 🌟 Skilled in ETL, Data Engineering, Machine Learning, and IoT-driven Solutions.
- 🏆 Certified Azure Data Engineer Associate.
- ⚡ Fun Fact: After my class hours, you’ll find me wrestling with vanishing gradients, taming activation functions, and convincing loss functions to take the hint — all in the name of 'convergence'. 🤖📐📉
- 🌱 What I'm Up To: Currently diving deep into MLOps to explore the building and deployement of end to end Machine Learning pipelines.
1️⃣ Programming Languages
2️⃣ ETL Tools & Distributed Systems
3️⃣ Databases
4️⃣ Machine Learning Models
5️⃣ Data Modeling
Here’s a list of repositories from the BigDataTeam5 organization that can be included in your GitHub profile's README:
-
master-financial-database
Repository for managing financial data with Python. -
AI-Info-Extractor_Markdown_Viewer
Forked project for extracting and visualizing AI-related information using markdown. -
Incremental DataPipeline using Snowflake
Developed an efficient ETL pipeline with incremental loading capabilities using Snowflake. -
LiteLLM SummaryGenerator with Q&A
Python-based project for summarization and question answering with LiteLLM. -
Building a RAG Pipeline with Airflow
Implemented RAG concepts to reduce input tokens in a language model pipeline. -
Nvidia-Agentic-Architecture-Workflow
Built workflows to integrate agentic architectures with FastAPI and Streamlit. -
Multi-Agentic Hackathon Project
A multi-agent system for crime analysis reports hosted on Streamlit. -
MarketScope AI-Powered Industry Segment Intelligence Platform
A multifaceted application for healthcare vendors utilizing LangGraph and Airflow.
- Azure Spotify ML Pipeline
Built scalable ETL pipelines and Random Forest models achieving an R² score of 0.82. - Motor Vehicles Crash Analysis
Analyzed crash data using Power BI and Talend, reducing traffic incidents by 35%. - Kansas City Service Request Analysis
Processed 1.56M service requests to optimize resource planning by 25%.
