SYS_001
Advanced Analytics / ML
COVID-19 Risk Profiles
Identifying multivariate risk patterns in 30M+ open health records for ICU prioritization.
30M+records analyzed
9
risk profiles
PythonK-MeansFuzzy C-Means
Explore
Data Science student building real infrastructure —
from EEG signal processing to open-source LLM clusters.
02. Featured Systems
Featured Projects
Selected systems // 2024—2025
SYS_002
Mobility / Data Viz
NYC Ride-Hailing Analytics
Stakeholders needed reliable insights across Uber/Lyft trip patterns and airport pricing.
R² .85fare prediction
92%
classification acc.
StreamlitScikit-learnPython
ExploreSYS_003
India Air Quality Intelligence
Cloud ETL architecture using Azure Databricks, PySpark, and PostgreSQL for continuous analytics.
2M+
daily records
500+
IoT sensors
SYSTEMS ARCHITECTURE // HIGH-FIDELITY INTERFACES // EDITORIAL DESIGN // SCALABLE ENGINEERING // SYSTEMS ARCHITECTURE // HIGH-FIDELITY INTERFACES // EDITORIAL DESIGN // SCALABLE ENGINEERING // SYSTEMS ARCHITECTURE // HIGH-FIDELITY INTERFACES // EDITORIAL DESIGN // SCALABLE ENGINEERING // SYSTEMS ARCHITECTURE // HIGH-FIDELITY INTERFACES // EDITORIAL DESIGN // SCALABLE ENGINEERING //
03. Systems & Capabilities
Architecture & Scale
SYS_01
Machine Learning Pipelines
End-to-end orchestration: from EEG signal processing and feature engineering to production-ready LLM clusters and model deployment.
Scikit-learnPyTorchMLflowGPU Clusters
SYS_02
Data Engineering & Infrastructure
ETL pipelines with PySpark and SQL, automated with n8n and Grafana, backed by Redis and high-performance GPU clusters.
PySparkRedisn8nDocker
SYS_03
Analytics Products
High-accuracy decision systems and predictive dashboards built with FastAPI, Streamlit and Power BI for real-world impact.
FastAPIStreamlitPower BISQL
SYS_04
Scalable Web Platforms
Modern full-stack ecosystems using Next.js, React, and TypeScript, optimized for high performance and seamless AI integrations.
Next.jsTypeScriptVercelTailwind
04. Working Principles
How I Think
I dont build demos. I build systems that survive Monday morning.
PRINCIPLE_01
Ship the pipeline, not the notebook
A Jupyter notebook is a prototype. A pipeline with monitoring, alerting, and a rollback plan is a product. I optimize for the person who gets paged at 3 AM, not the one clapping at the demo.
PRINCIPLE_02
Infrastructure is a feature
Fast models mean nothing if your deployment takes 45 minutes and your GPU cluster idles at 12%. I treat provisioning, orchestration, and cost control as first-class engineering problems.
PRINCIPLE_03
Explain it to the CEO or it didn't happen
If a stakeholder can't understand why the model made that decision, the model is broken — regardless of its accuracy. Clarity is not documentation. Clarity is design.
PRINCIPLE_01
Ship the pipeline, not the notebook
A Jupyter notebook is a prototype. A pipeline with monitoring, alerting, and a rollback plan is a product. I optimize for the person who gets paged at 3 AM, not the one clapping at the demo.
05. Technical Stack & Tooling
Technologies & Tooling
>stack.audit() — 29 tools across 4 domains — all systems nominal