Languages
Python · C · C++ · Java · SwiftUI · UIKit · HTML
I'm an electronics & information engineer specializing in computer vision, deep learning, and embedded systems. I build instruments that think — from U-Net segmentation to magnetic-resonance power transfer.
Areas of expertise
I am a BEI passout from IOE Thapathali Campus, building a practice around the idea that rigorous engineering can feel editorial. My work ranges from U-Net brain-tumor segmentation to magnetic-resonance wireless power transfer.
I am an engineer who identifies the need, solves the problem and experiments until it works. I have a genuine love for hardware — oscilloscopes, coils, PCBs — and I am deeply interested in research and mathematics. If it can be measured, modelled or optimised, I want to be the one doing it.
Python · C · C++ · Java · SwiftUI · UIKit · HTML
CNNs · U-Net · MLPs · Segmentation · Classification · CV pipelines · Model evaluation
PyTorch · TensorFlow · Keras · OpenCV · NumPy · Pandas · Scikit-learn · Django · Next.js · React · MQTT · WebSockets
MySQL · PostgreSQL · MongoDB · Firebase · Supabase
ESP32 · ESP-NOW · LTSpice · Ansys Maxwell · Custom PCB design
DSA · OOP · OS · Networks · DBMS · System design
I drew this rig on paper — V1, SW1, 470 Ω, 100 mH, 47 µF, D1 — photographed it, and taught the site to read it. Press test my work: Otsu thresholding, component detection, wire tracing, a clean vector redraw — and the sketch finally deploys as a live instrument you can drive.
A computer-vision pipeline that detects components, resolves connections and emits simulation-ready netlists from hand-drawn or scanned schematics.
A mid-range magnetic-resonance power transfer system with custom resonant coils and LC networks. Published; presented at OKRP 2025.
A U-Net trained on MRI scans to segment tumor regions with strong Dice and IoU scores, with a focus on reproducible training & clean evaluation.
Multi-camera person re-ID system using YOLO detection, ByteTrack for multi-object tracking, and OSNet appearance embeddings for cross-view matching.
Sequential RANSAC on skeletonized edge pixels to detect structural lines from hand-drawn cuboids, with corner snapping and six comparative methods.
Fine-tuning the TrOCR transformer model to recognize handwritten text from scanned documents, targeting low-legibility inputs with custom datasets.
Solar IoT drip-irrigation with ESP-NOW sensor nodes, a Django backend and a Flutter control app. Field-deployed, low-power design.
ESP32 streaming sensor data to a Django backend over MQTT and WebSockets with a live dashboard.
A GUI desktop tool for AES, RSA, hybrid encryption and cryptographic hashing — designed around clarity, not clutter.
A custom printed circuit board for a high-frequency RF amplifier — designed, fabricated and bench-tested.
A SwiftUI music app with real audio playback, Dynamic Island live activity, lock screen controls, playlists and an adaptive theme system. Zero dependencies.
A cross-platform desktop budget tracker built with Tauri, React and TypeScript, backed by a Rust core for native performance.
A tool built on the Manim engine to programmatically generate mathematical animations and visualisations for teaching and presentation.
Role-based Android application for student task management, assignment tracking and notifications.
Published in the KEC Journal of Science and Engineering (KJSE), Volume 10. Presented at the OKRP Conference 2025 on December 13, 2025.
DOI: 10.3126/kjse.v10i1.93856
B.E. in Electronics, Communication & Information Engineering · 7th semester
Computer Programming · OOP · Probability & Statistics · DSA · DBMS · OS · Computer Networks · Calculus · Linear Algebra · Discrete Mathematics · Machine Learning
Available for select freelance builds, research collaborations and full-time roles. I reply within a day, usually faster.