Sarvagya
Singh
Building high-performance web applications and design systems. Specialized in frontend architecture, TypeScript ecosystems, and scaling user interfaces for millions of users.
I’m Sarvagya.
Growing up in Bokaro Steel City taught me early that real impact happens when ideas meet everyday constraints. I spend my time exploring how intelligent systems can solve problems that actually matter in the world around us.
At Delhi Public School Bokaro I keep my academics sharp while quietly building and testing ideas late into the night. Every project reminds me that the best solutions feel simple and reliable once they reach the people who need them.
I am drawn to the places where computer science meets real-world complexity. Whether I am refining models under tight hardware limits or designing systems that must work without perfect conditions, I focus on clarity, robustness, and genuine usefulness.
Companies that value thoughtful engineering and hands-on problem solving tend to notice the same pattern in my work. I bring the same quiet determination and curiosity to every team I join.
I am ready for the next challenge.
Engineered for
Computational Rigor.
AI & Machine Learning
Physics-Informed & Clinical Intelligence
Edge Computing & IoT
Real-World Deployment
Robotics & Computer Vision
Autonomous Systems
Full-Stack & Platforms
Scalable Applications
Deployed Systems &
Validated Research.
Pulsage: Clinical AI System
Multimodal Deep Learning
Architected a dual-modal CNN ensemble fusing 12-lead ECG and cMRI data for Hypertrophic Cardiomyopathy detection. Validated with 98.5% sensitivity at Bokaro General Hospital.
Key Result 01
98.5% Accuracy
Key Result 02
Global Rank 1
Key Result 03
ACES ISRC
PINN Framework: Photon Transport
Computational Physics
Developed a Physics-Informed Neural Network (PINN) to approximate photon transport. Achieved a 10,000x speedup over traditional Monte Carlo sampling with <2% error regimes.
Key Result 01
10,000x Speedup
Key Result 02
UNESCO Global Award
Key Result 03
Scientific Creativity
Nandani: Edge-AIoT Platform
Veterinary Diagnostics
Designed LSTM-based anomaly detection for livestock health via embedded IoT collars. Reduced false positives by 40% and deployed across 40+ rural farms.
Key Result 01
40+ Rural Farms
Key Result 02
National Rank 2
Key Result 03
40% FP Reduction
Selected Work.
UNESCO International Year of Quantum Science
Awarded Research • 2025
Whispers of Light: Physics-Informed Neural Network for Photon Propagation
Built a PINN model that directly embeds differential equations for scattering, absorption, and refraction in biological tissue. Achieved 10,000× speedup over traditional Monte Carlo methods while maintaining high physical accuracy.
NUS Yong Loo Lin School of Medicine Collaboration
AI in Healthcare • 2025
PromptBiotic: Domain-Adapted Clinical LLM System
Developed a retrieval-augmented, adapter-tuned large language model for clinical and nutritional decision support. Focused on reducing hallucinations through structured medical grounding and safety validation.
World Robot Olympiad National Finals
Robotics & Computer Vision • 2025
Autonomous Structural Inspection Rover
Led the only team from Jharkhand to the National Finals (All India Rank 15). Designed a LiDAR + CV system for early detection of cracks and stress in infrastructure, optimised for real-world deployment on resource-constrained hardware.
Professional
Milestones.
2025 — Present
Full-Stack Developer
Education India
Architecting a high-end institutional platform connecting educators. Focused on minimalist UI refinement and scalable backend infrastructure using Next.js and Prisma.
Output_Log
- System Architecture
- UI Refinement
- Database Scaling
Summer 2024
AI Research Fellow
IISER Bhopal
Selected for the top 7% of applicants. Developed RAG-based clinical decision support and PINN frameworks for medical diagnostics.
Output_Log
- Top 7% Selection
- RAG Systems
- PINN Development
2024
Computational Researcher
University of Hawaii (Sci-mi)
Developed PINN frameworks for photon transport simulation. Achieved a 10,000x speedup over traditional Monte Carlo sampling methods.
Output_Log
- 10,000x Speedup
- PDE Constrained ML
- UNESCO Recognized
2023 — 2024
Lead AI Researcher
Pulsage System
Built a multimodal CNN ensemble for HCM detection. Validated at Bokaro General Hospital with 98.5% sensitivity across 200+ patients.
Output_Log
- 98.5% Accuracy
- Clinical Validation
- Global Rank 1
Milestones that define me.
UNESCO Quantum Science Competition
Physics-Informed Neural Network (PINN) framework for photon behavior simulation. Awarded for Scientific Creativity.
ACES ISRC Cardiac AI Competition
Architected Pulsage: a multimodal ECG/cMRI diagnostic ensemble with 98.5% sensitivity. Validated at Bokaro General Hospital.
IISER Bhopal Summer Fellowship
Selected from 3,500+ applicants for advanced research in RAG systems and computational biology.
World Robotics Olympiad (WRO)
Developed an autonomous structural health monitoring rover using LiDAR fusion and real-time computer vision.
NIT Industry Academia Conclave
National recognition for GauSeva AI (Nandani), an IoT-edge platform for cattle health anomaly detection.
Trusted voices.
Real impact.
“The PulseSage system demonstrates exceptional depth in cardiac diagnostics. The model’s 98.5% sensitivity and clear saliency mapping make it a viable tool for clinical assistance.”
Dr. Rajesh Kumar
Cardiologist, Bokaro General Hospital
“Sarvagya's research rigor is outstanding. He brings a unique combination of computational creativity and technical discipline to every complex problem he tackles.”
Prof. Afshar Alam
Vice-Chancellor, Jamia Hamdard
“As a developer, he consistently delivers high-integrity code. His work on database schema optimization and system architecture significantly improved our infrastructure performance.”
Sarthak Siddhant
Lead, Education India
Media
Archive.
The Researchers
DPS Bokaro student innovates ‘Nandini’ AI App to transform cattle health
Jharkhand Story
Projects of students qualify for NCSC national final
VARNANLIVE
New Innovation to help detect faults in buildings
Prabhat Khabar
Student Innovator Ranks Second at NIT Jamshedpur
Academic Excellence Weekly
Research Scholar Selected for IISER Bhopal Program
Dainik Bhaskar
Team Qualifies for World Robot Olympiad Nationals
Let’s collaborate.
I’m always open to research initiatives, engineering challenges, and high-impact AI/ML projects.
Let's build something real.
Open to research collaborations, startup opportunities, or just a conversation about AI that actually works in the real world.
Send me a message
"The best technology isn't the most advanced.
It's the one that actually reaches the people who need it most."
— Sarvagya Singh