I am a B.Tech Information Technology student passionate about developing intelligent systems that solve real-world challenges across healthcare, infrastructure, and industrial analytics.

My work focuses on:

• 🤖 Artificial Intelligence
• 👁️ Computer Vision
• 🧠 Explainable AI (XAI)
• 📊 Data Analytics
• 🏗️ Construction Quality Intelligence
• 🌐 Full-Stack Intelligent Applications

🏥 Healthcare AI

🏗️ Infrastructure Inspection & Civil Engineering AI

📊 Industrial Analytics & Six Sigma Intelligence

🧠 Explainable Machine Learning Systems

🚀 AI Product Development & Deployment

Academic & Engineering Focus
Artificial Intelligence • Machine Learning • Computer Vision • Data Analytics • Software Engineering

Python • Java • JavaScript • TypeScript • HTML • CSS • SQL

PyTorch • OpenCV • YOLO • ResNet • Deep Learning • Computer Vision • Explainable AI • Grad-CAM • RAG • Agentic AI

Pandas • NumPy • Plotly • Streamlit • Statistical Analytics • Six Sigma • Data Visualization

Google Cloud Platform • Google Cloud Run • Hugging Face Spaces • Render • Railway • Vercel • Docker

FastAPI • Flask • REST APIs • React • Next.js • Streamlit

Git • GitHub • VS Code • Docker • GitHub Actions • CI/CD

Applied AI • Explainable AI • Agentic Systems • Computer Vision • Digital Twins • Quality Intelligence

ForgeMind Rail is an evidence-grounded AI platform designed to connect fragmented railway asset information with predictive maintenance intelligence.

Instead of presenting an unsupported AI recommendation, the architecture is designed around a traceable engineering workflow:

The platform explores how inspection evidence, asset condition, operational context and AI-generated intelligence can be combined into a reviewable maintenance-support environment.

Safety Boundary: ForgeMind Rail provides engineering decision support. Operational maintenance actions are not autonomously executed.

Predict earlier → Explain why → Show the evidence → Let engineers decide

Panoramic Dental X-ray → Validation → Multi-Model AI → Evidence → Routing → XAI → Human Review

EndoXAI-RCT is an Explainable AI research and software platform investigating how heterogeneous AI models can be orchestrated to support structured review of panoramic dental radiographs in the context of Root Canal Treatment (RCT) assessment.

Rather than ending with defect detection or a single prediction score, the system extends the AI pipeline toward evidence-grounded, explainable and human-governed clinical decision support.

A conventional workflow may end at:

EndoXAI-RCT goes further:

The system is designed to ask not only:

“What did the AI predict?”

but also:

“Which model produced the evidence?”
“What supports the result?”
“How can the model behaviour be explained?”
“What must remain under human review?”

The associated engineering research investigates:

How can heterogeneous AI models, evidence, explainability and human review be orchestrated into a deployable clinical-image decision-support architecture?

The work is represented by:

Accepted for presentation at ICRISET 2026.

Architectural focus:

Model-role separation • Primary/advisory routing • Health-aware deployment • Failure-aware fallback • Evidence-aligned visualization • Artifact persistence • Human-in-the-loop review

⚕️ Responsible AI Notice: EndoXAI-RCT is a research and engineering prototype and is not an autonomous diagnostic system or medical device. Final clinical interpretation remains with qualified healthcare professionals.

🧠 Models explain • 🔎 Evidence supports • 👩‍⚕️ Humans decide

SentinelOps Nexus is an enterprise operational intelligence and Digital Twin platform developed around human-governed AI decision support.

The project was developed in connection with the AI Agent Builder Series 2026 Grand Finale in Bengaluru, following selection among the Top 100 AI Agent Builders from the community.

Rather than allowing an AI agent to directly execute operational decisions, SentinelOps Nexus follows a governance-first pattern:

SentinelOps Nexus is designed around a simple boundary:

AI may detect, analyse, explain and recommend — but consequential operational action remains human-controlled.

This separates decision intelligence from decision authority.

Top 100 AI Agent Builder — AI Agent Builder Series 2026

Grand Finale Participant — Bengaluru

Detect → Understand → Ground → Recommend → Review → Decide

DQIP transforms routine quality records into decision-ready engineering intelligence.

Instead of limiting analysis to pass/fail compliance, DQIP combines statistical quality analytics, Six Sigma process capability, abnormality detection, risk intelligence, corrective-action guidance and executive reporting.

🏗️ Construction   •   🏭 Manufacturing   •   🔬 Laboratory QA   •   🏥 Healthcare   •   💊 Pharmaceuticals   •   🌱 Environmental Monitoring

Traditional quality systems often answer:

“Did the result pass or fail?”

DQIP goes further:

“Is the process stable?”
“Is it capable?”
“Where is variation developing?”
“What is driving the risk?”
“What should be investigated next?”

The Construction Quality workspace is the validated demonstration workflow and includes:

• ✅ Concrete cube-strength evaluation
• ✅ Grade-aware acceptance analysis
• ✅ ACI/IS-oriented quality intelligence
• ✅ Sigma Level evaluation
• ✅ Cp, Cpk, Pp and Ppk analysis
• ✅ Coefficient of Variation monitoring
• ✅ Supplier and mix-performance comparison
• ✅ Statistical process monitoring
• ✅ Quality-risk identification
• ✅ Corrective-action guidance

Validation Note: Other domain workspaces are illustrative profiles and require independent domain validation before production use.

Transforming quality records into transparent, actionable and defensible intelligence.

See what is happening now • Understand every patient journey • Prepare for what comes next

CareScope Analytics is a frontend-only Healthcare Analytics SaaS platform designed as an interactive hospital operations command center.

It brings together:

The Hospital Digital Twin provides an interactive view of:

Emergency → ICU → Radiology → OPD → Pharmacy

with department-level information for:

👥 Patient Load • 🧑‍⚕️ Staff • 🛏️ Capacity • 🚦 Status • 🔔 Alerts

🔒 No Backend • No Database • No Authentication Service • No External API

All data is generated from internally consistent typed mock datasets, allowing the complete product experience to operate as a frontend demonstration.

⚕️ Demonstration Notice: All patient records, diagnoses, laboratory values, forecasts and operational metrics are fictional. CareScope Analytics is not intended for clinical diagnosis, treatment decisions or real hospital operations.

An Explainable Deep Learning framework developed for automated concrete crack detection, classification and visual interpretation.

YOLOv8 • ResNet-18 • Grad-CAM • OpenCV • Flask

✅ Automated Crack Detection
✅ Deep-Learning Classification
✅ Grad-CAM Explainability
✅ Visual Evidence Generation
✅ Infrastructure Inspection Intelligence

Explainable Deep Learning Framework for Automated Concrete Crack Detection Using ResNet-18

Published in the International Journal of Engineering Research & Technology (IJERT).

A full-stack web application designed for NGO workflow automation, project management and management-information reporting.

Core Features

✅ Project Lifecycle Management
✅ Resource Allocation
✅ MIS Reporting
✅ Dashboard Analytics
✅ User Authentication

Technology: Flask • MySQL • JavaScript • HTML • CSS

A data-driven market analytics application designed around technical indicators and automated trading-signal generation.

Capabilities

✅ RSI Strategy
✅ Moving Average Signals
✅ Telegram Alerts
✅ Time-Series Analytics

Data Analytics & Machine Learning Intern

Construction Quality Analytics • Infrastructure Intelligence • Explainable AI • Data-Driven Engineering

Data Analytics Intern

Predictive Analytics • Data Preprocessing • EDA • Machine Learning

Web Development Intern

Responsive Web Applications • Frontend Development • API Integration • UI/UX

Artificial Intelligence • Machine Learning • Computer Vision • Explainable AI • AI Agents • Digital Twins • Data Analytics • Full-Stack Engineering

AI Engineering • Machine Learning • Computer Vision • Explainable AI •
Agentic AI • Digital Twins • Cloud Deployment • Data Analytics

🧠 Advanced Deep Learning
🤖 Agentic AI Systems
⚡ MLOps & AI Deployment
☁️ AI + Cloud Integration
🔍 Explainable Computer Vision
🌐 Digital Twins
📊 Industrial AI Systems

Building AI systems that do more than predict — systems that explain, ground their outputs in evidence, support human decisions and translate research into deployable engineering.

AI Engineering • Research • Explainability • Human-Governed Intelligence