Real-Time Analytics Platform on AWS designed to ingest, process, and visualize high-volume streaming data from IoT devices and application logs.
Ingestion: Device telemetry (IoT Core) and application logs are published into Amazon Kinesis Data Streams, followed by lightweight routing and enrichment using AWS Lambda.
Processing & Storage: Amazon EMR performs heavy data transformations via Spark Structured Streaming, landing the curated output into Amazon S3 as partitioned Parquet files. AWS Glue then handles batch transformations before loading the data into Amazon Redshift for the analytics workload.
Orchestration & Serving: AWS Step Functions coordinate the batch processing workflows. Finally, Amazon QuickSight generates actionable business dashboards while Amazon CloudWatch monitors operational metrics and alarms
0
508
π‘ GA4 Funnel Tracking & Looker Studio Dashboard | Real Estate
A real estate client on Upwork had plenty of traffic but no idea where leads were slipping away. π
βοΈ What I did:
β Set up GA4 funnel tracking from first visit to booked call
π Built path explorations to spot where users drop off
π Combined GA4 + OptinMonster data into one landing page report
π Designed a Looker Studio dashboard the whole team can read at a glance
π The result:
The team finally saw which pages convert, which donβt, and exactly what to fix first. π―
π Client data is confidential, so visuals use sample data.
1
2
394
Built an intelligent inventory management system that automates stock ordering using machine learning and AI agents. Leveraging an XGBoost-based forecasting model, the system predicts future inventory demand and proactively places purchase orders when shortages are detected. The backend is powered by Django, integrated with AWS-hosted datasets for scalability and real-time data access. AI agents handle autonomous procurement decisions, reducing manual oversight and streamlining supply chain operations for greater efficiency and accuracy.
LakeShield - AI-Powered Video Monitoring and Vessel Intelligence Platform
I led the development of LakeShield as the Senior AI/ML Engineer and Lead Developer, taking the platform from initial research and experimentation to a scalable production system.
My responsibilities included:
πΉ Designing the end-to-end AI and video-processing architecture
πΉ Building YOLO-based boat and vehicle detection pipelines
πΉ Developing object tracking and movement-analysis workflows
πΉ Implementing OCR for extracting boat registration information
πΉ Creating scalable pipelines for processing thousands of surveillance videos
πΉ Developing FastAPI backend services and automated data workflows
πΉ Building a Next.js analytics dashboard integrated with Supabase
πΉ Deploying and operating the AI pipeline on cloud GPU infrastructure
πΉ Optimizing model accuracy, inference speed, infrastructure costs, and reliability
πΉ Managing production monitoring, troubleshooting, maintenance, and continuous improvements
The platform transforms raw surveillance footage into structured operational insights, enabling automated vessel monitoring, vehicle activity analysis, registration extraction, and reporting.
This project involved complete technical ownership across Computer Vision, AI/ML, backend development, cloud infrastructure, data engineering, MLOps, and production operations.
#ComputerVision #VideoAnalytics #ArtificialIntelligence #ObjectDetection #OCR #MLOps #FastAPI #NextJS #Supabase #CloudEngineering
π Sharing Task 2 of my Python Programming Internship at CodeAlpha (https://www.linkedin.com/company/codealpha/)!
This project is a Stock Portfolio Tracker built in Python. The user enters stock names and quantities, and the program calculates the total investment value using a hardcoded dictionary of stock prices (like AAPL, TSLA, GOOGL, and more).
It validates input, lets you add multiple stocks, displays a clean summary table and optionally saves the results to a .txt or .csv file.
I also built a bonus browser-based version using HTML, CSS, and JavaScript with a live-updating portfolio table, a dropdown to select stocks and a one-click CSV download feature.
Through this task, I got hands-on practice with:
β Dictionaries for structured data storage
β Input/output handling and validation
β Basic arithmetic for real-world calculations
β File handling (.txt and .csv export)
β Translating backend logic into an interactive front-end
Thankful to CodeAlpha for this practical learning experience on to the next task!
π GitHub repo link: https://lnkd.in/dswwqvYU
(https://lnkd.in/dswwqvYU)hashtag#CodeAlpha (https://www.linkedin.com/search/results/all/?keywords=%23codealpha&origin=HASH_TAG_FROM_FEED) hashtag#PythonProgramming (https://www.linkedin.com/search/results/all/?keywords=%23pythonprogramming&origin=HASH_TAG_FROM_FEED) hashtag#Internship (https://www.linkedin.com/search/results/all/?keywords=%23internship&origin=HASH_TAG_FROM_FEED) hashtag#LearningByDoing (https://www.linkedin.com/search/results/all/?keywords=%23learningbydoing&origin=HASH_TAG_FROM_FEED) hashtag#SoftwareDevelopment (https://www.linkedin.com/search/results/all/?keywords=%23softwaredevelopment&origin=HASH_TAG_FROM_FEED) hashtag#StudentDeveloper (https://www.linkedin.com/search/results/all/?keywords=%23studentdeveloper&origin=HASH_TAG_FROM_FEED) hashtag#BSCS (https://www.linkedin.com/search/results/all/?keywords=%23bscs&origin=HASH_TAG_FROM_FEED)
0
55
Built AuraChat v3.0 β a fully offline Document Intelligence desktop app in pure Python. Users upload any PDF, Word, or TXT file and ask questions in plain English. The system returns cited answers with confidence scores instantly.
Technical highlights:
β Custom NLP engine using TF-IDF scoring + hybrid token overlap analysis
β 1,700Γ faster indexing than baseline on 500-page documents
β Multi-threaded processing β UI never freezes during heavy indexing
β Supports PDF, DOCX, and TXT file formats
β Zero external APIs β runs completely offline on the user's machine
β 23 production-grade bugs identified and resolved before delivery
This is not a demo. This is production-ready software built with clean architecture, full error handling, keyboard shortcuts, chat export, source citations, and confidence indicators
I created a professionally formatted Microsoft Word document featuring a clean layout, structured headings, organized paragraphs, bullet points, and well-designed tables.
The project demonstrates my ability to create polished, readable, and visually consistent documents using Microsoft Word.